|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 14.999909559555032, |
|
"global_step": 82920, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"eval_loss": 6.646472930908203, |
|
"eval_runtime": 693.7508, |
|
"eval_samples_per_second": 21.75, |
|
"eval_steps_per_second": 2.72, |
|
"eval_wer": 1.0, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_loss": 3.0149917602539062, |
|
"eval_runtime": 593.4559, |
|
"eval_samples_per_second": 25.426, |
|
"eval_steps_per_second": 3.18, |
|
"eval_wer": 1.0, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"eval_loss": 2.8622469902038574, |
|
"eval_runtime": 589.8045, |
|
"eval_samples_per_second": 25.583, |
|
"eval_steps_per_second": 3.199, |
|
"eval_wer": 1.0003352779454167, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_loss": 0.9505894780158997, |
|
"eval_runtime": 590.9695, |
|
"eval_samples_per_second": 25.533, |
|
"eval_steps_per_second": 3.193, |
|
"eval_wer": 0.9770547966082064, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002988, |
|
"loss": 5.1598, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"eval_loss": 0.4883461594581604, |
|
"eval_runtime": 589.517, |
|
"eval_samples_per_second": 25.596, |
|
"eval_steps_per_second": 3.201, |
|
"eval_wer": 1.0009143943965912, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"eval_loss": 0.3893147110939026, |
|
"eval_runtime": 590.0583, |
|
"eval_samples_per_second": 25.572, |
|
"eval_steps_per_second": 3.198, |
|
"eval_wer": 1.0202507879031717, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 0.3416591286659241, |
|
"eval_runtime": 591.5909, |
|
"eval_samples_per_second": 25.506, |
|
"eval_steps_per_second": 3.19, |
|
"eval_wer": 1.0283218424437495, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"eval_loss": 0.33519014716148376, |
|
"eval_runtime": 589.9365, |
|
"eval_samples_per_second": 25.577, |
|
"eval_steps_per_second": 3.199, |
|
"eval_wer": 1.033539986466963, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_loss": 0.29870787262916565, |
|
"eval_runtime": 587.4241, |
|
"eval_samples_per_second": 25.687, |
|
"eval_steps_per_second": 3.212, |
|
"eval_wer": 1.0167699932334815, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00029818733317156027, |
|
"loss": 0.3671, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_loss": 0.2921440303325653, |
|
"eval_runtime": 590.6258, |
|
"eval_samples_per_second": 25.547, |
|
"eval_steps_per_second": 3.195, |
|
"eval_wer": 1.0159104625006858, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"eval_loss": 0.27703604102134705, |
|
"eval_runtime": 589.3558, |
|
"eval_samples_per_second": 25.603, |
|
"eval_steps_per_second": 3.202, |
|
"eval_wer": 1.009595045201563, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_loss": 0.2790297865867615, |
|
"eval_runtime": 590.1481, |
|
"eval_samples_per_second": 25.568, |
|
"eval_steps_per_second": 3.198, |
|
"eval_wer": 1.039812732027578, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"eval_loss": 0.2659136652946472, |
|
"eval_runtime": 597.7345, |
|
"eval_samples_per_second": 25.244, |
|
"eval_steps_per_second": 3.157, |
|
"eval_wer": 1.0189706357479442, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"eval_loss": 0.26571863889694214, |
|
"eval_runtime": 588.3253, |
|
"eval_samples_per_second": 25.647, |
|
"eval_steps_per_second": 3.207, |
|
"eval_wer": 1.0527727486085965, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.000296367386556661, |
|
"loss": 0.289, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 0.25557756423950195, |
|
"eval_runtime": 589.1568, |
|
"eval_samples_per_second": 25.611, |
|
"eval_steps_per_second": 3.203, |
|
"eval_wer": 1.0300530958346288, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_loss": 0.251380980014801, |
|
"eval_runtime": 588.0098, |
|
"eval_samples_per_second": 25.661, |
|
"eval_steps_per_second": 3.209, |
|
"eval_wer": 1.0192693379174973, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"eval_loss": 0.2708043158054352, |
|
"eval_runtime": 587.7443, |
|
"eval_samples_per_second": 25.673, |
|
"eval_steps_per_second": 3.211, |
|
"eval_wer": 1.0698658278622069, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"eval_loss": 0.2454645037651062, |
|
"eval_runtime": 588.52, |
|
"eval_samples_per_second": 25.639, |
|
"eval_steps_per_second": 3.206, |
|
"eval_wer": 1.0723468846582909, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"eval_loss": 0.2456223964691162, |
|
"eval_runtime": 588.2037, |
|
"eval_samples_per_second": 25.653, |
|
"eval_steps_per_second": 3.208, |
|
"eval_wer": 1.0099851868107752, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00029454743994176166, |
|
"loss": 0.271, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_loss": 0.23379947245121002, |
|
"eval_runtime": 589.0243, |
|
"eval_samples_per_second": 25.617, |
|
"eval_steps_per_second": 3.204, |
|
"eval_wer": 1.0532665215827557, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_loss": 0.24785736203193665, |
|
"eval_runtime": 589.1749, |
|
"eval_samples_per_second": 25.61, |
|
"eval_steps_per_second": 3.203, |
|
"eval_wer": 1.012795425589632, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 0.2482644021511078, |
|
"eval_runtime": 588.4854, |
|
"eval_samples_per_second": 25.64, |
|
"eval_steps_per_second": 3.207, |
|
"eval_wer": 1.0385691556482142, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"eval_loss": 0.2435576617717743, |
|
"eval_runtime": 588.7455, |
|
"eval_samples_per_second": 25.629, |
|
"eval_steps_per_second": 3.205, |
|
"eval_wer": 1.052827612272392, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"eval_loss": 0.23819999396800995, |
|
"eval_runtime": 588.1659, |
|
"eval_samples_per_second": 25.654, |
|
"eval_steps_per_second": 3.208, |
|
"eval_wer": 1.0476094682491786, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0002927274933268624, |
|
"loss": 0.2634, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"eval_loss": 0.23290811479091644, |
|
"eval_runtime": 586.0097, |
|
"eval_samples_per_second": 25.749, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0680492309943124, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"eval_loss": 0.24330949783325195, |
|
"eval_runtime": 588.1907, |
|
"eval_samples_per_second": 25.653, |
|
"eval_steps_per_second": 3.208, |
|
"eval_wer": 1.0581067159220447, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"eval_loss": 0.23539048433303833, |
|
"eval_runtime": 586.7811, |
|
"eval_samples_per_second": 25.715, |
|
"eval_steps_per_second": 3.216, |
|
"eval_wer": 1.0640990472010388, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"eval_loss": 0.23182104527950287, |
|
"eval_runtime": 587.761, |
|
"eval_samples_per_second": 25.672, |
|
"eval_steps_per_second": 3.21, |
|
"eval_wer": 1.0504197070280354, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"eval_loss": 0.2324739396572113, |
|
"eval_runtime": 586.8577, |
|
"eval_samples_per_second": 25.712, |
|
"eval_steps_per_second": 3.215, |
|
"eval_wer": 1.0500112775308912, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0002909075467119631, |
|
"loss": 0.2522, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"eval_loss": 0.23437276482582092, |
|
"eval_runtime": 587.0455, |
|
"eval_samples_per_second": 25.703, |
|
"eval_steps_per_second": 3.214, |
|
"eval_wer": 1.0380083270849716, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"eval_loss": 0.22438600659370422, |
|
"eval_runtime": 586.7245, |
|
"eval_samples_per_second": 25.717, |
|
"eval_steps_per_second": 3.216, |
|
"eval_wer": 1.0662996897155015, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"eval_loss": 0.23398412764072418, |
|
"eval_runtime": 612.4912, |
|
"eval_samples_per_second": 24.635, |
|
"eval_steps_per_second": 3.081, |
|
"eval_wer": 1.0646781636522131, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"eval_loss": 0.22881384193897247, |
|
"eval_runtime": 585.7737, |
|
"eval_samples_per_second": 25.759, |
|
"eval_steps_per_second": 3.221, |
|
"eval_wer": 1.053760294556915, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"eval_loss": 0.22119460999965668, |
|
"eval_runtime": 586.2268, |
|
"eval_samples_per_second": 25.739, |
|
"eval_steps_per_second": 3.219, |
|
"eval_wer": 1.0614473034509244, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0002890876000970638, |
|
"loss": 0.2468, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"eval_loss": 0.24868042767047882, |
|
"eval_runtime": 586.4723, |
|
"eval_samples_per_second": 25.728, |
|
"eval_steps_per_second": 3.218, |
|
"eval_wer": 1.0557414824161957, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"eval_loss": 0.23298682272434235, |
|
"eval_runtime": 585.8307, |
|
"eval_samples_per_second": 25.757, |
|
"eval_steps_per_second": 3.221, |
|
"eval_wer": 1.0509561517407022, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 0.230791836977005, |
|
"eval_runtime": 585.3799, |
|
"eval_samples_per_second": 25.776, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0506330657205734, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"eval_loss": 0.2320248782634735, |
|
"eval_runtime": 583.445, |
|
"eval_samples_per_second": 25.862, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.0450796437519432, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"eval_loss": 0.22605428099632263, |
|
"eval_runtime": 586.6782, |
|
"eval_samples_per_second": 25.719, |
|
"eval_steps_per_second": 3.216, |
|
"eval_wer": 1.0701462421438281, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0002872676534821645, |
|
"loss": 0.2505, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"eval_loss": 0.22813868522644043, |
|
"eval_runtime": 585.3181, |
|
"eval_samples_per_second": 25.779, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0713288588967527, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"eval_loss": 0.22771993279457092, |
|
"eval_runtime": 585.9383, |
|
"eval_samples_per_second": 25.752, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0741147138250338, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"eval_loss": 0.2253136932849884, |
|
"eval_runtime": 586.3951, |
|
"eval_samples_per_second": 25.732, |
|
"eval_steps_per_second": 3.218, |
|
"eval_wer": 1.0814237730351188, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"eval_loss": 0.22151607275009155, |
|
"eval_runtime": 585.0731, |
|
"eval_samples_per_second": 25.79, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0437141481197003, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"eval_loss": 0.2219705879688263, |
|
"eval_runtime": 585.6079, |
|
"eval_samples_per_second": 25.766, |
|
"eval_steps_per_second": 3.222, |
|
"eval_wer": 1.0557475783788397, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0002854477068672652, |
|
"loss": 0.2434, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"eval_loss": 0.21836136281490326, |
|
"eval_runtime": 585.1783, |
|
"eval_samples_per_second": 25.785, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.053327481209195, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 0.22221527993679047, |
|
"eval_runtime": 585.7348, |
|
"eval_samples_per_second": 25.761, |
|
"eval_steps_per_second": 3.222, |
|
"eval_wer": 1.0818809702334145, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"eval_loss": 0.21622225642204285, |
|
"eval_runtime": 583.8059, |
|
"eval_samples_per_second": 25.846, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0237681583487257, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"eval_loss": 0.21315866708755493, |
|
"eval_runtime": 586.2817, |
|
"eval_samples_per_second": 25.737, |
|
"eval_steps_per_second": 3.219, |
|
"eval_wer": 1.0456831440536933, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"eval_loss": 0.2067827582359314, |
|
"eval_runtime": 586.0493, |
|
"eval_samples_per_second": 25.747, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0611425053187273, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.00028362776025236594, |
|
"loss": 0.2347, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"eval_loss": 0.21656368672847748, |
|
"eval_runtime": 587.7097, |
|
"eval_samples_per_second": 25.674, |
|
"eval_steps_per_second": 3.211, |
|
"eval_wer": 1.033229092372122, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"eval_loss": 0.20866595208644867, |
|
"eval_runtime": 584.4202, |
|
"eval_samples_per_second": 25.819, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.043324006510488, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"eval_loss": 0.20998135209083557, |
|
"eval_runtime": 584.1559, |
|
"eval_samples_per_second": 25.83, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0291813731765451, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"eval_loss": 0.20666413009166718, |
|
"eval_runtime": 596.9283, |
|
"eval_samples_per_second": 25.278, |
|
"eval_steps_per_second": 3.161, |
|
"eval_wer": 1.0733892942704046, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"eval_loss": 0.21476301550865173, |
|
"eval_runtime": 586.1885, |
|
"eval_samples_per_second": 25.741, |
|
"eval_steps_per_second": 3.219, |
|
"eval_wer": 1.0278646452454538, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0002818078136374666, |
|
"loss": 0.2333, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"eval_loss": 0.21248245239257812, |
|
"eval_runtime": 583.9808, |
|
"eval_samples_per_second": 25.838, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0276695744408477, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"eval_loss": 0.20541033148765564, |
|
"eval_runtime": 585.3036, |
|
"eval_samples_per_second": 25.78, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0453234822577007, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"eval_loss": 0.20914313197135925, |
|
"eval_runtime": 587.377, |
|
"eval_samples_per_second": 25.689, |
|
"eval_steps_per_second": 3.213, |
|
"eval_wer": 1.0556927147150443, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"eval_loss": 0.20860984921455383, |
|
"eval_runtime": 586.6064, |
|
"eval_samples_per_second": 25.723, |
|
"eval_steps_per_second": 3.217, |
|
"eval_wer": 1.0238900776016044, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"eval_loss": 0.20505470037460327, |
|
"eval_runtime": 585.9549, |
|
"eval_samples_per_second": 25.751, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0645074766981828, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0002799878670225673, |
|
"loss": 0.2087, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"eval_loss": 0.21026617288589478, |
|
"eval_runtime": 586.0996, |
|
"eval_samples_per_second": 25.745, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0239876130039076, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"eval_loss": 0.21449421346187592, |
|
"eval_runtime": 637.0564, |
|
"eval_samples_per_second": 23.686, |
|
"eval_steps_per_second": 2.962, |
|
"eval_wer": 1.019726535115793, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"eval_loss": 0.21362827718257904, |
|
"eval_runtime": 584.7089, |
|
"eval_samples_per_second": 25.806, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.024761800259688, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"eval_loss": 0.20446062088012695, |
|
"eval_runtime": 585.0534, |
|
"eval_samples_per_second": 25.791, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0443359363093823, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"eval_loss": 0.20893406867980957, |
|
"eval_runtime": 584.0987, |
|
"eval_samples_per_second": 25.833, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0396969087373433, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.000278167920407668, |
|
"loss": 0.2013, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"eval_loss": 0.20124834775924683, |
|
"eval_runtime": 590.5862, |
|
"eval_samples_per_second": 25.549, |
|
"eval_steps_per_second": 3.195, |
|
"eval_wer": 1.06541577513213, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"eval_loss": 0.20543764531612396, |
|
"eval_runtime": 586.1833, |
|
"eval_samples_per_second": 25.741, |
|
"eval_steps_per_second": 3.219, |
|
"eval_wer": 1.0414342580908664, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"eval_loss": 0.20810039341449738, |
|
"eval_runtime": 584.4277, |
|
"eval_samples_per_second": 25.818, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.0631846528044475, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"eval_loss": 0.21040508151054382, |
|
"eval_runtime": 584.8815, |
|
"eval_samples_per_second": 25.798, |
|
"eval_steps_per_second": 3.226, |
|
"eval_wer": 1.0189645397853002, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 0.20450659096240997, |
|
"eval_runtime": 650.9655, |
|
"eval_samples_per_second": 23.179, |
|
"eval_steps_per_second": 2.899, |
|
"eval_wer": 1.0812835658943083, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00027634797379276873, |
|
"loss": 0.2092, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"eval_loss": 0.20958924293518066, |
|
"eval_runtime": 584.7926, |
|
"eval_samples_per_second": 25.802, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.0751449315118597, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"eval_loss": 0.21034906804561615, |
|
"eval_runtime": 585.9876, |
|
"eval_samples_per_second": 25.75, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0327597032485385, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"eval_loss": 0.20439012348651886, |
|
"eval_runtime": 584.5735, |
|
"eval_samples_per_second": 25.812, |
|
"eval_steps_per_second": 3.228, |
|
"eval_wer": 1.0011094652011971, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"eval_loss": 0.20891864597797394, |
|
"eval_runtime": 600.6694, |
|
"eval_samples_per_second": 25.12, |
|
"eval_steps_per_second": 3.141, |
|
"eval_wer": 1.0259748968258322, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"eval_loss": 0.20627248287200928, |
|
"eval_runtime": 585.2007, |
|
"eval_samples_per_second": 25.784, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0550648305627184, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.00027452802717786945, |
|
"loss": 0.2076, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"eval_loss": 0.20286831259727478, |
|
"eval_runtime": 584.7246, |
|
"eval_samples_per_second": 25.805, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.0074919380894034, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"eval_loss": 0.20403894782066345, |
|
"eval_runtime": 583.776, |
|
"eval_samples_per_second": 25.847, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.05280932438446, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"eval_loss": 0.20745955407619476, |
|
"eval_runtime": 604.3868, |
|
"eval_samples_per_second": 24.966, |
|
"eval_steps_per_second": 3.122, |
|
"eval_wer": 1.039824923952866, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"eval_loss": 0.20228976011276245, |
|
"eval_runtime": 585.3687, |
|
"eval_samples_per_second": 25.777, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0231280822711117, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"eval_loss": 0.20485945045948029, |
|
"eval_runtime": 583.728, |
|
"eval_samples_per_second": 25.849, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.0318331169266595, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.0002727080805629701, |
|
"loss": 0.2028, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"eval_loss": 0.20722831785678864, |
|
"eval_runtime": 583.7841, |
|
"eval_samples_per_second": 25.847, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0762909724889207, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"eval_loss": 0.20749975740909576, |
|
"eval_runtime": 584.061, |
|
"eval_samples_per_second": 25.835, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.07615076534811, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"eval_loss": 0.20522591471672058, |
|
"eval_runtime": 584.4057, |
|
"eval_samples_per_second": 25.819, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.0838072944288997, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"eval_loss": 0.20528368651866913, |
|
"eval_runtime": 585.178, |
|
"eval_samples_per_second": 25.785, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0407088385362375, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"eval_loss": 0.20656365156173706, |
|
"eval_runtime": 582.9655, |
|
"eval_samples_per_second": 25.883, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0265844930902264, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.00027089177384130066, |
|
"loss": 0.2025, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"eval_loss": 0.20365557074546814, |
|
"eval_runtime": 618.5483, |
|
"eval_samples_per_second": 24.394, |
|
"eval_steps_per_second": 3.051, |
|
"eval_wer": 1.0628432788963869, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"eval_loss": 0.20097516477108002, |
|
"eval_runtime": 587.6824, |
|
"eval_samples_per_second": 25.675, |
|
"eval_steps_per_second": 3.211, |
|
"eval_wer": 1.0351432246423193, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"eval_loss": 0.19610826671123505, |
|
"eval_runtime": 622.9403, |
|
"eval_samples_per_second": 24.222, |
|
"eval_steps_per_second": 3.029, |
|
"eval_wer": 1.0811799345293611, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"eval_loss": 0.19632692635059357, |
|
"eval_runtime": 575.4893, |
|
"eval_samples_per_second": 26.219, |
|
"eval_steps_per_second": 3.279, |
|
"eval_wer": 1.0867516443859233, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"eval_loss": 0.20223282277584076, |
|
"eval_runtime": 608.9116, |
|
"eval_samples_per_second": 24.78, |
|
"eval_steps_per_second": 3.099, |
|
"eval_wer": 1.0710118688392678, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.0002690718272264013, |
|
"loss": 0.1997, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"eval_loss": 0.20513388514518738, |
|
"eval_runtime": 598.4671, |
|
"eval_samples_per_second": 25.213, |
|
"eval_steps_per_second": 3.153, |
|
"eval_wer": 1.076449467517663, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"eval_loss": 0.19871561229228973, |
|
"eval_runtime": 590.1203, |
|
"eval_samples_per_second": 25.569, |
|
"eval_steps_per_second": 3.198, |
|
"eval_wer": 1.0580579482208934, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"eval_loss": 0.2050638645887375, |
|
"eval_runtime": 605.4186, |
|
"eval_samples_per_second": 24.923, |
|
"eval_steps_per_second": 3.117, |
|
"eval_wer": 1.0611425053187273, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"eval_loss": 0.19992168247699738, |
|
"eval_runtime": 583.3088, |
|
"eval_samples_per_second": 25.868, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0808263686960127, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"eval_loss": 0.19722315669059753, |
|
"eval_runtime": 584.2218, |
|
"eval_samples_per_second": 25.828, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0703230250605025, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00026725552050473186, |
|
"loss": 0.1983, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"eval_loss": 0.19610898196697235, |
|
"eval_runtime": 595.3314, |
|
"eval_samples_per_second": 25.346, |
|
"eval_steps_per_second": 3.17, |
|
"eval_wer": 1.0583749382783783, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"eval_loss": 0.20308014750480652, |
|
"eval_runtime": 581.8181, |
|
"eval_samples_per_second": 25.934, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0938107691276069, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"eval_loss": 0.20190203189849854, |
|
"eval_runtime": 587.8215, |
|
"eval_samples_per_second": 25.669, |
|
"eval_steps_per_second": 3.21, |
|
"eval_wer": 1.0891229738544161, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"eval_loss": 0.20063284039497375, |
|
"eval_runtime": 584.1697, |
|
"eval_samples_per_second": 25.83, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0542418756057863, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"eval_loss": 0.19250920414924622, |
|
"eval_runtime": 585.7179, |
|
"eval_samples_per_second": 25.762, |
|
"eval_steps_per_second": 3.222, |
|
"eval_wer": 1.0627091677182203, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.00026543557388983253, |
|
"loss": 0.1961, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"eval_loss": 0.19760142266750336, |
|
"eval_runtime": 583.2305, |
|
"eval_samples_per_second": 25.871, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0750595880348446, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"eval_loss": 0.20509831607341766, |
|
"eval_runtime": 591.9667, |
|
"eval_samples_per_second": 25.49, |
|
"eval_steps_per_second": 3.188, |
|
"eval_wer": 1.0611120255055078, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"eval_loss": 0.20372095704078674, |
|
"eval_runtime": 583.6045, |
|
"eval_samples_per_second": 25.855, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.0655986540114482, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"eval_loss": 0.20245492458343506, |
|
"eval_runtime": 583.3003, |
|
"eval_samples_per_second": 25.868, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0291326054753935, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"eval_loss": 0.1976877748966217, |
|
"eval_runtime": 583.6653, |
|
"eval_samples_per_second": 25.852, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.052510622214907, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00026361562727493325, |
|
"loss": 0.2025, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"eval_loss": 0.2030467540025711, |
|
"eval_runtime": 587.811, |
|
"eval_samples_per_second": 25.67, |
|
"eval_steps_per_second": 3.21, |
|
"eval_wer": 1.0669885334942668, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"eval_loss": 0.1979692280292511, |
|
"eval_runtime": 584.4024, |
|
"eval_samples_per_second": 25.82, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.0765165231067464, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"eval_loss": 0.19752389192581177, |
|
"eval_runtime": 584.2228, |
|
"eval_samples_per_second": 25.827, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0254140682625896, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"eval_loss": 0.19863851368427277, |
|
"eval_runtime": 584.6885, |
|
"eval_samples_per_second": 25.807, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.0636052742268796, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"eval_loss": 0.19562380015850067, |
|
"eval_runtime": 584.0348, |
|
"eval_samples_per_second": 25.836, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0351676084928951, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.000261795680660034, |
|
"loss": 0.2025, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"eval_loss": 0.19542592763900757, |
|
"eval_runtime": 583.716, |
|
"eval_samples_per_second": 25.85, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.0265479173143628, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"eval_loss": 0.19573526084423065, |
|
"eval_runtime": 585.187, |
|
"eval_samples_per_second": 25.785, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.075218083063587, |
|
"step": 11100 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"eval_loss": 0.19426105916500092, |
|
"eval_runtime": 582.8174, |
|
"eval_samples_per_second": 25.89, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0783818876757922, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"eval_loss": 0.1898316591978073, |
|
"eval_runtime": 614.8974, |
|
"eval_samples_per_second": 24.539, |
|
"eval_steps_per_second": 3.069, |
|
"eval_wer": 1.0341130069554934, |
|
"step": 11300 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"eval_loss": 0.19210608303546906, |
|
"eval_runtime": 584.1617, |
|
"eval_samples_per_second": 25.83, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0301445352742877, |
|
"step": 11400 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00025997573404513464, |
|
"loss": 0.1805, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"eval_loss": 0.19096077978610992, |
|
"eval_runtime": 581.9805, |
|
"eval_samples_per_second": 25.927, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.023006163018233, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"eval_loss": 0.19605235755443573, |
|
"eval_runtime": 582.7853, |
|
"eval_samples_per_second": 25.891, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.020311747529611, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"eval_loss": 0.1973300278186798, |
|
"eval_runtime": 673.0903, |
|
"eval_samples_per_second": 22.417, |
|
"eval_steps_per_second": 2.803, |
|
"eval_wer": 1.0776198923452998, |
|
"step": 11700 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"eval_loss": 0.18762777745723724, |
|
"eval_runtime": 583.2234, |
|
"eval_samples_per_second": 25.872, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0787598373597167, |
|
"step": 11800 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"eval_loss": 0.19344566762447357, |
|
"eval_runtime": 590.5519, |
|
"eval_samples_per_second": 25.551, |
|
"eval_steps_per_second": 3.195, |
|
"eval_wer": 1.0251153660930366, |
|
"step": 11900 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.00025815578743023537, |
|
"loss": 0.177, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"eval_loss": 0.1967364251613617, |
|
"eval_runtime": 582.7068, |
|
"eval_samples_per_second": 25.895, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0339971836652584, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"eval_loss": 0.19323694705963135, |
|
"eval_runtime": 614.0473, |
|
"eval_samples_per_second": 24.573, |
|
"eval_steps_per_second": 3.073, |
|
"eval_wer": 1.0131428954603365, |
|
"step": 12100 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"eval_loss": 0.19259363412857056, |
|
"eval_runtime": 583.7904, |
|
"eval_samples_per_second": 25.847, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0077784483336687, |
|
"step": 12200 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"eval_loss": 0.19467875361442566, |
|
"eval_runtime": 592.864, |
|
"eval_samples_per_second": 25.451, |
|
"eval_steps_per_second": 3.183, |
|
"eval_wer": 0.9991404692672043, |
|
"step": 12300 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"eval_loss": 0.191410094499588, |
|
"eval_runtime": 584.2417, |
|
"eval_samples_per_second": 25.827, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.021262717702066, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 0.00025633584081533603, |
|
"loss": 0.1782, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"eval_loss": 0.19619227945804596, |
|
"eval_runtime": 633.7228, |
|
"eval_samples_per_second": 23.81, |
|
"eval_steps_per_second": 2.978, |
|
"eval_wer": 0.9882469840224819, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"eval_loss": 0.19596128165721893, |
|
"eval_runtime": 581.5084, |
|
"eval_samples_per_second": 25.948, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0562230634650671, |
|
"step": 12600 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"eval_loss": 0.20055778324604034, |
|
"eval_runtime": 584.0758, |
|
"eval_samples_per_second": 25.834, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0400687624586236, |
|
"step": 12700 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"eval_loss": 0.19500796496868134, |
|
"eval_runtime": 582.9458, |
|
"eval_samples_per_second": 25.884, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0687502666983657, |
|
"step": 12800 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"eval_loss": 0.19202886521816254, |
|
"eval_runtime": 667.6773, |
|
"eval_samples_per_second": 22.599, |
|
"eval_steps_per_second": 2.826, |
|
"eval_wer": 1.0435312692403822, |
|
"step": 12900 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.00025451589420043676, |
|
"loss": 0.1796, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"eval_loss": 0.19256320595741272, |
|
"eval_runtime": 583.0382, |
|
"eval_samples_per_second": 25.88, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0667081192126455, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"eval_loss": 0.19494299590587616, |
|
"eval_runtime": 594.068, |
|
"eval_samples_per_second": 25.399, |
|
"eval_steps_per_second": 3.176, |
|
"eval_wer": 1.0858799217278396, |
|
"step": 13100 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"eval_loss": 0.19322112202644348, |
|
"eval_runtime": 583.3591, |
|
"eval_samples_per_second": 25.866, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0670373011954182, |
|
"step": 13200 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"eval_loss": 0.1882387101650238, |
|
"eval_runtime": 593.7714, |
|
"eval_samples_per_second": 25.412, |
|
"eval_steps_per_second": 3.178, |
|
"eval_wer": 1.0663484574166529, |
|
"step": 13300 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"eval_loss": 0.18768326938152313, |
|
"eval_runtime": 583.1762, |
|
"eval_samples_per_second": 25.874, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0759983662820114, |
|
"step": 13400 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.00025269958747876724, |
|
"loss": 0.1775, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"eval_loss": 0.18931668996810913, |
|
"eval_runtime": 582.2322, |
|
"eval_samples_per_second": 25.916, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0858799217278396, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"eval_loss": 0.19357560575008392, |
|
"eval_runtime": 582.3494, |
|
"eval_samples_per_second": 25.911, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0702315856208433, |
|
"step": 13600 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"eval_loss": 0.18714427947998047, |
|
"eval_runtime": 729.8014, |
|
"eval_samples_per_second": 20.675, |
|
"eval_steps_per_second": 2.586, |
|
"eval_wer": 1.0413854903897148, |
|
"step": 13700 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"eval_loss": 0.19174307584762573, |
|
"eval_runtime": 582.2533, |
|
"eval_samples_per_second": 25.915, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0430009204903592, |
|
"step": 13800 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"eval_loss": 0.19221140444278717, |
|
"eval_runtime": 582.224, |
|
"eval_samples_per_second": 25.916, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.042208445346647, |
|
"step": 13900 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 0.00025087964086386796, |
|
"loss": 0.1778, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"eval_loss": 0.1874552071094513, |
|
"eval_runtime": 584.0031, |
|
"eval_samples_per_second": 25.837, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0584846656059692, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"eval_loss": 0.18758933246135712, |
|
"eval_runtime": 585.1267, |
|
"eval_samples_per_second": 25.788, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0603195503617955, |
|
"step": 14100 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"eval_loss": 0.18875516951084137, |
|
"eval_runtime": 581.9395, |
|
"eval_samples_per_second": 25.929, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.062837182933743, |
|
"step": 14200 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"eval_loss": 0.1948392391204834, |
|
"eval_runtime": 583.5666, |
|
"eval_samples_per_second": 25.857, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.078217296684406, |
|
"step": 14300 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"eval_loss": 0.19421540200710297, |
|
"eval_runtime": 583.5382, |
|
"eval_samples_per_second": 25.858, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.069536645879434, |
|
"step": 14400 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 0.0002490596942489687, |
|
"loss": 0.1784, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"eval_loss": 0.18421576917171478, |
|
"eval_runtime": 702.5128, |
|
"eval_samples_per_second": 21.479, |
|
"eval_steps_per_second": 2.686, |
|
"eval_wer": 1.086276159299696, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"eval_loss": 0.18499960005283356, |
|
"eval_runtime": 582.6097, |
|
"eval_samples_per_second": 25.899, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0542784513816499, |
|
"step": 14600 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"eval_loss": 0.18243639171123505, |
|
"eval_runtime": 582.7743, |
|
"eval_samples_per_second": 25.892, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0683479331638657, |
|
"step": 14700 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"eval_loss": 0.1887967884540558, |
|
"eval_runtime": 584.0929, |
|
"eval_samples_per_second": 25.833, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0693110952616083, |
|
"step": 14800 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"eval_loss": 0.1871066838502884, |
|
"eval_runtime": 649.9925, |
|
"eval_samples_per_second": 23.214, |
|
"eval_steps_per_second": 2.903, |
|
"eval_wer": 1.0174771249001786, |
|
"step": 14900 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 0.00024723974763406935, |
|
"loss": 0.1753, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"eval_loss": 0.1888967603445053, |
|
"eval_runtime": 583.1751, |
|
"eval_samples_per_second": 25.874, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0548636637954683, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"eval_loss": 0.18651245534420013, |
|
"eval_runtime": 582.2511, |
|
"eval_samples_per_second": 25.915, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0543881787092408, |
|
"step": 15100 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"eval_loss": 0.19178926944732666, |
|
"eval_runtime": 582.2685, |
|
"eval_samples_per_second": 25.914, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0725907231640484, |
|
"step": 15200 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"eval_loss": 0.19644701480865479, |
|
"eval_runtime": 591.4992, |
|
"eval_samples_per_second": 25.51, |
|
"eval_steps_per_second": 3.19, |
|
"eval_wer": 1.0915003992855532, |
|
"step": 15300 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"eval_loss": 0.1900092214345932, |
|
"eval_runtime": 582.3923, |
|
"eval_samples_per_second": 25.909, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0610205860658486, |
|
"step": 15400 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 0.0002454198010191701, |
|
"loss": 0.1768, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"eval_loss": 0.1893770694732666, |
|
"eval_runtime": 581.8947, |
|
"eval_samples_per_second": 25.931, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.076254396713057, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"eval_loss": 0.18816040456295013, |
|
"eval_runtime": 582.1192, |
|
"eval_samples_per_second": 25.921, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0547905122437409, |
|
"step": 15600 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"eval_loss": 0.18607495725154877, |
|
"eval_runtime": 677.7124, |
|
"eval_samples_per_second": 22.265, |
|
"eval_steps_per_second": 2.784, |
|
"eval_wer": 1.0901531915412421, |
|
"step": 15700 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"eval_loss": 0.18599402904510498, |
|
"eval_runtime": 582.8742, |
|
"eval_samples_per_second": 25.887, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0551379821144455, |
|
"step": 15800 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"eval_loss": 0.1878904402256012, |
|
"eval_runtime": 583.6205, |
|
"eval_samples_per_second": 25.854, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.058094523996757, |
|
"step": 15900 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 0.0002435998544042708, |
|
"loss": 0.1761, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"eval_loss": 0.18994924426078796, |
|
"eval_runtime": 582.1435, |
|
"eval_samples_per_second": 25.92, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0544369464103924, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"eval_loss": 0.18596774339675903, |
|
"eval_runtime": 667.4862, |
|
"eval_samples_per_second": 22.606, |
|
"eval_steps_per_second": 2.827, |
|
"eval_wer": 1.0530226830769982, |
|
"step": 16100 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"eval_loss": 0.1893654614686966, |
|
"eval_runtime": 582.0917, |
|
"eval_samples_per_second": 25.922, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0595697469565906, |
|
"step": 16200 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"eval_loss": 0.18347308039665222, |
|
"eval_runtime": 583.0288, |
|
"eval_samples_per_second": 25.88, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.039404302530434, |
|
"step": 16300 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"eval_loss": 0.18515755236148834, |
|
"eval_runtime": 582.7168, |
|
"eval_samples_per_second": 25.894, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0444883353754808, |
|
"step": 16400 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 0.00024178354768260128, |
|
"loss": 0.1754, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"eval_loss": 0.1847403347492218, |
|
"eval_runtime": 639.6413, |
|
"eval_samples_per_second": 23.59, |
|
"eval_steps_per_second": 2.95, |
|
"eval_wer": 1.0389836811080022, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.1828482747077942, |
|
"eval_runtime": 584.2229, |
|
"eval_samples_per_second": 25.827, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0440311381771852, |
|
"step": 16600 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"eval_loss": 0.18693839013576508, |
|
"eval_runtime": 595.3259, |
|
"eval_samples_per_second": 25.346, |
|
"eval_steps_per_second": 3.17, |
|
"eval_wer": 1.0559792249593094, |
|
"step": 16700 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"eval_loss": 0.18819798529148102, |
|
"eval_runtime": 594.2234, |
|
"eval_samples_per_second": 25.393, |
|
"eval_steps_per_second": 3.176, |
|
"eval_wer": 1.057277665002469, |
|
"step": 16800 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"eval_loss": 0.19123658537864685, |
|
"eval_runtime": 595.6382, |
|
"eval_samples_per_second": 25.332, |
|
"eval_steps_per_second": 3.168, |
|
"eval_wer": 1.0600269441548862, |
|
"step": 16900 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 0.000239963601067702, |
|
"loss": 0.1592, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"eval_loss": 0.19209939241409302, |
|
"eval_runtime": 581.7293, |
|
"eval_samples_per_second": 25.938, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0528702840108997, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"eval_loss": 0.18810659646987915, |
|
"eval_runtime": 589.251, |
|
"eval_samples_per_second": 25.607, |
|
"eval_steps_per_second": 3.202, |
|
"eval_wer": 1.0175137006760422, |
|
"step": 17100 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"eval_loss": 0.18914476037025452, |
|
"eval_runtime": 582.5239, |
|
"eval_samples_per_second": 25.903, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.06541577513213, |
|
"step": 17200 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"eval_loss": 0.18887841701507568, |
|
"eval_runtime": 611.0926, |
|
"eval_samples_per_second": 24.692, |
|
"eval_steps_per_second": 3.088, |
|
"eval_wer": 1.06872588284779, |
|
"step": 17300 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"eval_loss": 0.19159947335720062, |
|
"eval_runtime": 582.2026, |
|
"eval_samples_per_second": 25.917, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0641661027901221, |
|
"step": 17400 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 0.0002381436544528027, |
|
"loss": 0.1556, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"eval_loss": 0.1849842667579651, |
|
"eval_runtime": 593.9614, |
|
"eval_samples_per_second": 25.404, |
|
"eval_steps_per_second": 3.177, |
|
"eval_wer": 1.0295471309351816, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"eval_loss": 0.18748754262924194, |
|
"eval_runtime": 582.3741, |
|
"eval_samples_per_second": 25.909, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0272794328316357, |
|
"step": 17600 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"eval_loss": 0.1894107609987259, |
|
"eval_runtime": 613.1677, |
|
"eval_samples_per_second": 24.608, |
|
"eval_steps_per_second": 3.077, |
|
"eval_wer": 1.0051449924714861, |
|
"step": 17700 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"eval_loss": 0.18696586787700653, |
|
"eval_runtime": 581.7614, |
|
"eval_samples_per_second": 25.937, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.046201300878428, |
|
"step": 17800 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"eval_loss": 0.1830950528383255, |
|
"eval_runtime": 584.1829, |
|
"eval_samples_per_second": 25.829, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0308272830904093, |
|
"step": 17900 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 0.0002363237078379034, |
|
"loss": 0.1557, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"eval_loss": 0.18782374262809753, |
|
"eval_runtime": 581.3732, |
|
"eval_samples_per_second": 25.954, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0602829745859317, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"eval_loss": 0.18500719964504242, |
|
"eval_runtime": 608.8148, |
|
"eval_samples_per_second": 24.784, |
|
"eval_steps_per_second": 3.099, |
|
"eval_wer": 1.0565644373731278, |
|
"step": 18100 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"eval_loss": 0.18434764444828033, |
|
"eval_runtime": 581.6725, |
|
"eval_samples_per_second": 25.941, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0629225264107582, |
|
"step": 18200 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"eval_loss": 0.18864037096500397, |
|
"eval_runtime": 592.2707, |
|
"eval_samples_per_second": 25.477, |
|
"eval_steps_per_second": 3.186, |
|
"eval_wer": 1.037776680504502, |
|
"step": 18300 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"eval_loss": 0.18917690217494965, |
|
"eval_runtime": 582.1854, |
|
"eval_samples_per_second": 25.918, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.038081478636699, |
|
"step": 18400 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 0.0002345074011162339, |
|
"loss": 0.159, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"eval_loss": 0.19416740536689758, |
|
"eval_runtime": 606.7386, |
|
"eval_samples_per_second": 24.869, |
|
"eval_steps_per_second": 3.11, |
|
"eval_wer": 1.0519497936516644, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"eval_loss": 0.1828826367855072, |
|
"eval_runtime": 583.2506, |
|
"eval_samples_per_second": 25.871, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0621910108934853, |
|
"step": 18600 |
|
}, |
|
{ |
|
"epoch": 3.38, |
|
"eval_loss": 0.18944011628627777, |
|
"eval_runtime": 584.8676, |
|
"eval_samples_per_second": 25.799, |
|
"eval_steps_per_second": 3.226, |
|
"eval_wer": 1.0556683308644685, |
|
"step": 18700 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"eval_loss": 0.1894686222076416, |
|
"eval_runtime": 583.4404, |
|
"eval_samples_per_second": 25.862, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.0626543040544247, |
|
"step": 18800 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"eval_loss": 0.1863497793674469, |
|
"eval_runtime": 667.2283, |
|
"eval_samples_per_second": 22.614, |
|
"eval_steps_per_second": 2.828, |
|
"eval_wer": 1.0361917302170773, |
|
"step": 18900 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 0.0002326874545013346, |
|
"loss": 0.1582, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"eval_loss": 0.1887533962726593, |
|
"eval_runtime": 583.1359, |
|
"eval_samples_per_second": 25.876, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0491029790969442, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"eval_loss": 0.18543538451194763, |
|
"eval_runtime": 602.1626, |
|
"eval_samples_per_second": 25.058, |
|
"eval_steps_per_second": 3.134, |
|
"eval_wer": 1.0483287918411637, |
|
"step": 19100 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"eval_loss": 0.17971904575824738, |
|
"eval_runtime": 582.7463, |
|
"eval_samples_per_second": 25.893, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 0.9786580347835628, |
|
"step": 19200 |
|
}, |
|
{ |
|
"epoch": 3.49, |
|
"eval_loss": 0.17851972579956055, |
|
"eval_runtime": 599.5376, |
|
"eval_samples_per_second": 25.168, |
|
"eval_steps_per_second": 3.147, |
|
"eval_wer": 1.0086440750291081, |
|
"step": 19300 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"eval_loss": 0.17966009676456451, |
|
"eval_runtime": 582.3922, |
|
"eval_samples_per_second": 25.909, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 0.9914778442237706, |
|
"step": 19400 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 0.00023086750788643532, |
|
"loss": 0.1507, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"eval_loss": 0.18731391429901123, |
|
"eval_runtime": 592.8938, |
|
"eval_samples_per_second": 25.45, |
|
"eval_steps_per_second": 3.183, |
|
"eval_wer": 1.026627164828734, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"eval_loss": 0.18384875357151031, |
|
"eval_runtime": 582.4778, |
|
"eval_samples_per_second": 25.905, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0298946008058862, |
|
"step": 19600 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"eval_loss": 0.1817297637462616, |
|
"eval_runtime": 651.5542, |
|
"eval_samples_per_second": 23.158, |
|
"eval_steps_per_second": 2.896, |
|
"eval_wer": 1.035496790475668, |
|
"step": 19700 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"eval_loss": 0.1819145381450653, |
|
"eval_runtime": 584.5774, |
|
"eval_samples_per_second": 25.812, |
|
"eval_steps_per_second": 3.228, |
|
"eval_wer": 1.0271209378028932, |
|
"step": 19800 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"eval_loss": 0.1882605254650116, |
|
"eval_runtime": 584.3669, |
|
"eval_samples_per_second": 25.821, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.0248410477740593, |
|
"step": 19900 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 0.00022904756127153602, |
|
"loss": 0.1601, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"eval_loss": 0.18232683837413788, |
|
"eval_runtime": 583.0799, |
|
"eval_samples_per_second": 25.878, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.040556439470139, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"eval_loss": 0.1801084280014038, |
|
"eval_runtime": 752.5425, |
|
"eval_samples_per_second": 20.051, |
|
"eval_steps_per_second": 2.507, |
|
"eval_wer": 1.0260541443402036, |
|
"step": 20100 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"eval_loss": 0.17828203737735748, |
|
"eval_runtime": 584.7605, |
|
"eval_samples_per_second": 25.804, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.032899910389349, |
|
"step": 20200 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"eval_loss": 0.18572643399238586, |
|
"eval_runtime": 592.41, |
|
"eval_samples_per_second": 25.471, |
|
"eval_steps_per_second": 3.185, |
|
"eval_wer": 1.0161908767823071, |
|
"step": 20300 |
|
}, |
|
{ |
|
"epoch": 3.69, |
|
"eval_loss": 0.18137747049331665, |
|
"eval_runtime": 584.2029, |
|
"eval_samples_per_second": 25.828, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0211956621129825, |
|
"step": 20400 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 0.0002272276146566367, |
|
"loss": 0.1552, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"eval_loss": 0.18369783461093903, |
|
"eval_runtime": 679.994, |
|
"eval_samples_per_second": 22.19, |
|
"eval_steps_per_second": 2.775, |
|
"eval_wer": 1.0231768499722633, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"eval_loss": 0.18426425755023956, |
|
"eval_runtime": 583.2731, |
|
"eval_samples_per_second": 25.87, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.031357631840432, |
|
"step": 20600 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"eval_loss": 0.18420319259166718, |
|
"eval_runtime": 584.6255, |
|
"eval_samples_per_second": 25.81, |
|
"eval_steps_per_second": 3.228, |
|
"eval_wer": 1.0258042098718019, |
|
"step": 20700 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"eval_loss": 0.1821189969778061, |
|
"eval_runtime": 583.3576, |
|
"eval_samples_per_second": 25.866, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0479386502319514, |
|
"step": 20800 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"eval_loss": 0.18640317022800446, |
|
"eval_runtime": 583.5933, |
|
"eval_samples_per_second": 25.855, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.045920886596807, |
|
"step": 20900 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 0.0002254076680417374, |
|
"loss": 0.1576, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"eval_loss": 0.18312126398086548, |
|
"eval_runtime": 584.1144, |
|
"eval_samples_per_second": 25.832, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0364294727601908, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"eval_loss": 0.18524977564811707, |
|
"eval_runtime": 583.1667, |
|
"eval_samples_per_second": 25.874, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0271148418402491, |
|
"step": 21100 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"eval_loss": 0.18645203113555908, |
|
"eval_runtime": 582.2828, |
|
"eval_samples_per_second": 25.914, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0204458587077778, |
|
"step": 21200 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"eval_loss": 0.1793699860572815, |
|
"eval_runtime": 644.1191, |
|
"eval_samples_per_second": 23.426, |
|
"eval_steps_per_second": 2.93, |
|
"eval_wer": 1.0324305212657656, |
|
"step": 21300 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"eval_loss": 0.18262524902820587, |
|
"eval_runtime": 583.8148, |
|
"eval_samples_per_second": 25.846, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0315039349438866, |
|
"step": 21400 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 0.0002235877214268381, |
|
"loss": 0.1585, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"eval_loss": 0.18238940834999084, |
|
"eval_runtime": 588.9702, |
|
"eval_samples_per_second": 25.619, |
|
"eval_steps_per_second": 3.204, |
|
"eval_wer": 1.0326804557341673, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"eval_loss": 0.18375591933727264, |
|
"eval_runtime": 583.1374, |
|
"eval_samples_per_second": 25.876, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0207811366531947, |
|
"step": 21600 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"eval_loss": 0.1849592924118042, |
|
"eval_runtime": 583.4937, |
|
"eval_samples_per_second": 25.86, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.019909413995111, |
|
"step": 21700 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"eval_loss": 0.1841159164905548, |
|
"eval_runtime": 584.0991, |
|
"eval_samples_per_second": 25.833, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0050352651438952, |
|
"step": 21800 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"eval_loss": 0.178331658244133, |
|
"eval_runtime": 583.3943, |
|
"eval_samples_per_second": 25.864, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0003352779454167, |
|
"step": 21900 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 0.00022176777481193883, |
|
"loss": 0.1572, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"eval_loss": 0.17869696021080017, |
|
"eval_runtime": 582.8458, |
|
"eval_samples_per_second": 25.888, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0114726016958968, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.180954247713089, |
|
"eval_runtime": 583.446, |
|
"eval_samples_per_second": 25.862, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.0235426077308998, |
|
"step": 22100 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"eval_loss": 0.17629148066043854, |
|
"eval_runtime": 584.1606, |
|
"eval_samples_per_second": 25.83, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.019092555000823, |
|
"step": 22200 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"eval_loss": 0.1763954758644104, |
|
"eval_runtime": 583.2857, |
|
"eval_samples_per_second": 25.869, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.033222996409478, |
|
"step": 22300 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"eval_loss": 0.1793549805879593, |
|
"eval_runtime": 582.3125, |
|
"eval_samples_per_second": 25.912, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0428972891254122, |
|
"step": 22400 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 0.00021994782819703953, |
|
"loss": 0.1406, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"eval_loss": 0.1905169039964676, |
|
"eval_runtime": 671.5465, |
|
"eval_samples_per_second": 22.469, |
|
"eval_steps_per_second": 2.81, |
|
"eval_wer": 1.0287546557914693, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"eval_loss": 0.17760008573532104, |
|
"eval_runtime": 582.5998, |
|
"eval_samples_per_second": 25.899, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0244265223142712, |
|
"step": 22600 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"eval_loss": 0.17820368707180023, |
|
"eval_runtime": 595.3661, |
|
"eval_samples_per_second": 25.344, |
|
"eval_steps_per_second": 3.169, |
|
"eval_wer": 1.045085739714587, |
|
"step": 22700 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"eval_loss": 0.17709559202194214, |
|
"eval_runtime": 582.1208, |
|
"eval_samples_per_second": 25.921, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0387276506769567, |
|
"step": 22800 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"eval_loss": 0.17884837090969086, |
|
"eval_runtime": 645.9188, |
|
"eval_samples_per_second": 23.361, |
|
"eval_steps_per_second": 2.921, |
|
"eval_wer": 1.0434581176886548, |
|
"step": 22900 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 0.00021812788158214025, |
|
"loss": 0.14, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"eval_loss": 0.17918579280376434, |
|
"eval_runtime": 581.9318, |
|
"eval_samples_per_second": 25.929, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0420804301311242, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"eval_loss": 0.18405954539775848, |
|
"eval_runtime": 588.3849, |
|
"eval_samples_per_second": 25.645, |
|
"eval_steps_per_second": 3.207, |
|
"eval_wer": 1.0240546685929908, |
|
"step": 23100 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"eval_loss": 0.17691761255264282, |
|
"eval_runtime": 581.3629, |
|
"eval_samples_per_second": 25.955, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0545588656632712, |
|
"step": 23200 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"eval_loss": 0.18145306408405304, |
|
"eval_runtime": 719.2259, |
|
"eval_samples_per_second": 20.979, |
|
"eval_steps_per_second": 2.624, |
|
"eval_wer": 1.0601915351462727, |
|
"step": 23300 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"eval_loss": 0.1783633530139923, |
|
"eval_runtime": 581.7307, |
|
"eval_samples_per_second": 25.938, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0368683820705547, |
|
"step": 23400 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 0.00021630793496724095, |
|
"loss": 0.1394, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"eval_loss": 0.1808551549911499, |
|
"eval_runtime": 594.0637, |
|
"eval_samples_per_second": 25.4, |
|
"eval_steps_per_second": 3.176, |
|
"eval_wer": 1.0406356869845101, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"eval_loss": 0.17443229258060455, |
|
"eval_runtime": 582.3112, |
|
"eval_samples_per_second": 25.912, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0132831026011473, |
|
"step": 23600 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"eval_loss": 0.17706982791423798, |
|
"eval_runtime": 624.4614, |
|
"eval_samples_per_second": 24.163, |
|
"eval_steps_per_second": 3.022, |
|
"eval_wer": 1.021354157141725, |
|
"step": 23700 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"eval_loss": 0.17652854323387146, |
|
"eval_runtime": 582.3415, |
|
"eval_samples_per_second": 25.911, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.006394664813494, |
|
"step": 23800 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"eval_loss": 0.1792861521244049, |
|
"eval_runtime": 610.5223, |
|
"eval_samples_per_second": 24.715, |
|
"eval_steps_per_second": 3.091, |
|
"eval_wer": 1.0200008534347702, |
|
"step": 23900 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 0.00021448798835234167, |
|
"loss": 0.14, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"eval_loss": 0.1775696575641632, |
|
"eval_runtime": 582.2567, |
|
"eval_samples_per_second": 25.915, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0351737044555391, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"eval_loss": 0.1774866282939911, |
|
"eval_runtime": 589.1918, |
|
"eval_samples_per_second": 25.61, |
|
"eval_steps_per_second": 3.203, |
|
"eval_wer": 1.0294252116823028, |
|
"step": 24100 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"eval_loss": 0.1763463169336319, |
|
"eval_runtime": 582.7316, |
|
"eval_samples_per_second": 25.894, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0212810055899977, |
|
"step": 24200 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"eval_loss": 0.1697307527065277, |
|
"eval_runtime": 594.6072, |
|
"eval_samples_per_second": 25.376, |
|
"eval_steps_per_second": 3.174, |
|
"eval_wer": 1.0302237827886591, |
|
"step": 24300 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"eval_loss": 0.17706170678138733, |
|
"eval_runtime": 581.6621, |
|
"eval_samples_per_second": 25.941, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.025901745274105, |
|
"step": 24400 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 0.00021267532152390194, |
|
"loss": 0.1408, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"eval_loss": 0.17474128305912018, |
|
"eval_runtime": 600.4729, |
|
"eval_samples_per_second": 25.129, |
|
"eval_steps_per_second": 3.143, |
|
"eval_wer": 1.0409100053034874, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"eval_loss": 0.17691320180892944, |
|
"eval_runtime": 580.8883, |
|
"eval_samples_per_second": 25.976, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0278341654322343, |
|
"step": 24600 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"eval_loss": 0.17671321332454681, |
|
"eval_runtime": 581.8233, |
|
"eval_samples_per_second": 25.934, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0189950195985198, |
|
"step": 24700 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"eval_loss": 0.17452046275138855, |
|
"eval_runtime": 581.5649, |
|
"eval_samples_per_second": 25.946, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0280962918259238, |
|
"step": 24800 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"eval_loss": 0.17375342547893524, |
|
"eval_runtime": 581.0408, |
|
"eval_samples_per_second": 25.969, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0355577501021074, |
|
"step": 24900 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 0.00021085537490900266, |
|
"loss": 0.1391, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"eval_loss": 0.1780717819929123, |
|
"eval_runtime": 581.6537, |
|
"eval_samples_per_second": 25.942, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0429399608639198, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"eval_loss": 0.17844460904598236, |
|
"eval_runtime": 588.6313, |
|
"eval_samples_per_second": 25.634, |
|
"eval_steps_per_second": 3.206, |
|
"eval_wer": 1.0075894734917064, |
|
"step": 25100 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"eval_loss": 0.1770990788936615, |
|
"eval_runtime": 581.2924, |
|
"eval_samples_per_second": 25.958, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0156666239949281, |
|
"step": 25200 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"eval_loss": 0.17579950392246246, |
|
"eval_runtime": 591.9028, |
|
"eval_samples_per_second": 25.492, |
|
"eval_steps_per_second": 3.188, |
|
"eval_wer": 1.033728961308925, |
|
"step": 25300 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"eval_loss": 0.1758110374212265, |
|
"eval_runtime": 581.3785, |
|
"eval_samples_per_second": 25.954, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0466036344129284, |
|
"step": 25400 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 0.00020903542829410336, |
|
"loss": 0.1398, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"eval_loss": 0.1723676174879074, |
|
"eval_runtime": 614.5901, |
|
"eval_samples_per_second": 24.551, |
|
"eval_steps_per_second": 3.07, |
|
"eval_wer": 1.040330888852313, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"eval_loss": 0.17654301226139069, |
|
"eval_runtime": 580.7681, |
|
"eval_samples_per_second": 25.981, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.0480727614101182, |
|
"step": 25600 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"eval_loss": 0.17569170892238617, |
|
"eval_runtime": 619.4473, |
|
"eval_samples_per_second": 24.359, |
|
"eval_steps_per_second": 3.046, |
|
"eval_wer": 1.031979420030114, |
|
"step": 25700 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"eval_loss": 0.18143196403980255, |
|
"eval_runtime": 581.9906, |
|
"eval_samples_per_second": 25.927, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.047877690605512, |
|
"step": 25800 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"eval_loss": 0.17128212749958038, |
|
"eval_runtime": 607.3729, |
|
"eval_samples_per_second": 24.843, |
|
"eval_steps_per_second": 3.107, |
|
"eval_wer": 1.0251092701303925, |
|
"step": 25900 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 0.00020721548167920408, |
|
"loss": 0.1427, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"eval_loss": 0.1734877973794937, |
|
"eval_runtime": 581.7467, |
|
"eval_samples_per_second": 25.937, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0339971836652584, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"eval_loss": 0.1765192449092865, |
|
"eval_runtime": 590.7316, |
|
"eval_samples_per_second": 25.543, |
|
"eval_steps_per_second": 3.194, |
|
"eval_wer": 1.0358198764957969, |
|
"step": 26100 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"eval_loss": 0.17305831611156464, |
|
"eval_runtime": 582.6945, |
|
"eval_samples_per_second": 25.895, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.021975945331407, |
|
"step": 26200 |
|
}, |
|
{ |
|
"epoch": 4.76, |
|
"eval_loss": 0.17689305543899536, |
|
"eval_runtime": 596.8319, |
|
"eval_samples_per_second": 25.282, |
|
"eval_steps_per_second": 3.162, |
|
"eval_wer": 1.0261394878172188, |
|
"step": 26300 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"eval_loss": 0.1746763437986374, |
|
"eval_runtime": 580.7187, |
|
"eval_samples_per_second": 25.983, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.013923178678761, |
|
"step": 26400 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 0.00020539553506430477, |
|
"loss": 0.1424, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"eval_loss": 0.17905060946941376, |
|
"eval_runtime": 612.0357, |
|
"eval_samples_per_second": 24.654, |
|
"eval_steps_per_second": 3.083, |
|
"eval_wer": 1.040550343507495, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 4.81, |
|
"eval_loss": 0.17353174090385437, |
|
"eval_runtime": 581.1951, |
|
"eval_samples_per_second": 25.962, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0496577116975427, |
|
"step": 26600 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"eval_loss": 0.17099276185035706, |
|
"eval_runtime": 582.2823, |
|
"eval_samples_per_second": 25.914, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.043250854958761, |
|
"step": 26700 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"eval_loss": 0.1770693063735962, |
|
"eval_runtime": 581.9174, |
|
"eval_samples_per_second": 25.93, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0001828788793183, |
|
"step": 26800 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"eval_loss": 0.17479608952999115, |
|
"eval_runtime": 605.5155, |
|
"eval_samples_per_second": 24.919, |
|
"eval_steps_per_second": 3.116, |
|
"eval_wer": 1.004645123534683, |
|
"step": 26900 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 0.00020357558844940547, |
|
"loss": 0.1419, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"eval_loss": 0.1793585568666458, |
|
"eval_runtime": 579.9597, |
|
"eval_samples_per_second": 26.017, |
|
"eval_steps_per_second": 3.254, |
|
"eval_wer": 1.03324128429741, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"eval_loss": 0.17716261744499207, |
|
"eval_runtime": 589.6493, |
|
"eval_samples_per_second": 25.59, |
|
"eval_steps_per_second": 3.2, |
|
"eval_wer": 1.0557780581920595, |
|
"step": 27100 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"eval_loss": 0.1757478266954422, |
|
"eval_runtime": 580.361, |
|
"eval_samples_per_second": 25.999, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0477496753899893, |
|
"step": 27200 |
|
}, |
|
{ |
|
"epoch": 4.94, |
|
"eval_loss": 0.17353762686252594, |
|
"eval_runtime": 625.2736, |
|
"eval_samples_per_second": 24.132, |
|
"eval_steps_per_second": 3.018, |
|
"eval_wer": 1.0324122333778338, |
|
"step": 27300 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"eval_loss": 0.17579859495162964, |
|
"eval_runtime": 581.3776, |
|
"eval_samples_per_second": 25.954, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.025999280676408, |
|
"step": 27400 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 0.00020175564183450617, |
|
"loss": 0.1433, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"eval_loss": 0.17672304809093475, |
|
"eval_runtime": 580.2867, |
|
"eval_samples_per_second": 26.003, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0421535816828515, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"eval_loss": 0.1695006638765335, |
|
"eval_runtime": 579.8433, |
|
"eval_samples_per_second": 26.023, |
|
"eval_steps_per_second": 3.254, |
|
"eval_wer": 1.038587443536146, |
|
"step": 27600 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"eval_loss": 0.1763276606798172, |
|
"eval_runtime": 691.6775, |
|
"eval_samples_per_second": 21.815, |
|
"eval_steps_per_second": 2.728, |
|
"eval_wer": 1.057052114384643, |
|
"step": 27700 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"eval_loss": 0.17430032789707184, |
|
"eval_runtime": 582.2365, |
|
"eval_samples_per_second": 25.916, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0366672153033045, |
|
"step": 27800 |
|
}, |
|
{ |
|
"epoch": 5.05, |
|
"eval_loss": 0.1804419308900833, |
|
"eval_runtime": 589.7736, |
|
"eval_samples_per_second": 25.584, |
|
"eval_steps_per_second": 3.2, |
|
"eval_wer": 1.0254689319263852, |
|
"step": 27900 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 0.00019993933511283668, |
|
"loss": 0.1306, |
|
"step": 28000 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"eval_loss": 0.1802925318479538, |
|
"eval_runtime": 581.8829, |
|
"eval_samples_per_second": 25.931, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.037673049139555, |
|
"step": 28000 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"eval_loss": 0.17504069209098816, |
|
"eval_runtime": 581.7334, |
|
"eval_samples_per_second": 25.938, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.055211133666173, |
|
"step": 28100 |
|
}, |
|
{ |
|
"epoch": 5.1, |
|
"eval_loss": 0.17433439195156097, |
|
"eval_runtime": 581.8045, |
|
"eval_samples_per_second": 25.935, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0511573185079521, |
|
"step": 28200 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"eval_loss": 0.1777062863111496, |
|
"eval_runtime": 581.1315, |
|
"eval_samples_per_second": 25.965, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0583627463530902, |
|
"step": 28300 |
|
}, |
|
{ |
|
"epoch": 5.14, |
|
"eval_loss": 0.1725868433713913, |
|
"eval_runtime": 572.8216, |
|
"eval_samples_per_second": 26.342, |
|
"eval_steps_per_second": 3.294, |
|
"eval_wer": 1.0373682510073579, |
|
"step": 28400 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"learning_rate": 0.0001981193884979374, |
|
"loss": 0.123, |
|
"step": 28500 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"eval_loss": 0.17764069139957428, |
|
"eval_runtime": 580.2271, |
|
"eval_samples_per_second": 26.005, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0439214108495942, |
|
"step": 28500 |
|
}, |
|
{ |
|
"epoch": 5.17, |
|
"eval_loss": 0.17592105269432068, |
|
"eval_runtime": 581.0221, |
|
"eval_samples_per_second": 25.97, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0681955340977671, |
|
"step": 28600 |
|
}, |
|
{ |
|
"epoch": 5.19, |
|
"eval_loss": 0.17235223948955536, |
|
"eval_runtime": 580.265, |
|
"eval_samples_per_second": 26.004, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0511207427320886, |
|
"step": 28700 |
|
}, |
|
{ |
|
"epoch": 5.21, |
|
"eval_loss": 0.16769592463970184, |
|
"eval_runtime": 590.3886, |
|
"eval_samples_per_second": 25.558, |
|
"eval_steps_per_second": 3.196, |
|
"eval_wer": 1.0559670330340216, |
|
"step": 28800 |
|
}, |
|
{ |
|
"epoch": 5.23, |
|
"eval_loss": 0.16985873878002167, |
|
"eval_runtime": 580.2765, |
|
"eval_samples_per_second": 26.003, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0420682382058364, |
|
"step": 28900 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 0.00019629944188303807, |
|
"loss": 0.1217, |
|
"step": 29000 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"eval_loss": 0.18032023310661316, |
|
"eval_runtime": 580.8131, |
|
"eval_samples_per_second": 25.979, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.0369781093981456, |
|
"step": 29000 |
|
}, |
|
{ |
|
"epoch": 5.26, |
|
"eval_loss": 0.17702044546604156, |
|
"eval_runtime": 582.0629, |
|
"eval_samples_per_second": 25.923, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0473778216687089, |
|
"step": 29100 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"eval_loss": 0.17327551543712616, |
|
"eval_runtime": 581.4254, |
|
"eval_samples_per_second": 25.952, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0331864206336143, |
|
"step": 29200 |
|
}, |
|
{ |
|
"epoch": 5.3, |
|
"eval_loss": 0.17459562420845032, |
|
"eval_runtime": 581.5283, |
|
"eval_samples_per_second": 25.947, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0158312149863145, |
|
"step": 29300 |
|
}, |
|
{ |
|
"epoch": 5.32, |
|
"eval_loss": 0.1762886941432953, |
|
"eval_runtime": 581.9585, |
|
"eval_samples_per_second": 25.928, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0341130069554934, |
|
"step": 29400 |
|
}, |
|
{ |
|
"epoch": 5.34, |
|
"learning_rate": 0.00019447949526813876, |
|
"loss": 0.1246, |
|
"step": 29500 |
|
}, |
|
{ |
|
"epoch": 5.34, |
|
"eval_loss": 0.17754170298576355, |
|
"eval_runtime": 581.4218, |
|
"eval_samples_per_second": 25.952, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.034753083033107, |
|
"step": 29500 |
|
}, |
|
{ |
|
"epoch": 5.35, |
|
"eval_loss": 0.17297494411468506, |
|
"eval_runtime": 608.3786, |
|
"eval_samples_per_second": 24.802, |
|
"eval_steps_per_second": 3.102, |
|
"eval_wer": 1.0491761306486713, |
|
"step": 29600 |
|
}, |
|
{ |
|
"epoch": 5.37, |
|
"eval_loss": 0.17302390933036804, |
|
"eval_runtime": 582.277, |
|
"eval_samples_per_second": 25.914, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0502734039245807, |
|
"step": 29700 |
|
}, |
|
{ |
|
"epoch": 5.39, |
|
"eval_loss": 0.17274653911590576, |
|
"eval_runtime": 601.2418, |
|
"eval_samples_per_second": 25.096, |
|
"eval_steps_per_second": 3.139, |
|
"eval_wer": 1.0436958602317685, |
|
"step": 29800 |
|
}, |
|
{ |
|
"epoch": 5.41, |
|
"eval_loss": 0.17440034449100494, |
|
"eval_runtime": 582.4042, |
|
"eval_samples_per_second": 25.908, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0539065976603694, |
|
"step": 29900 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 0.00019266318854646927, |
|
"loss": 0.127, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"eval_loss": 0.17481261491775513, |
|
"eval_runtime": 585.1655, |
|
"eval_samples_per_second": 25.786, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.046311028206019, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"eval_loss": 0.17456230521202087, |
|
"eval_runtime": 668.4648, |
|
"eval_samples_per_second": 22.573, |
|
"eval_steps_per_second": 2.823, |
|
"eval_wer": 1.0554793560225062, |
|
"step": 30100 |
|
}, |
|
{ |
|
"epoch": 5.46, |
|
"eval_loss": 0.18095143139362335, |
|
"eval_runtime": 581.559, |
|
"eval_samples_per_second": 25.946, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0557963460799913, |
|
"step": 30200 |
|
}, |
|
{ |
|
"epoch": 5.48, |
|
"eval_loss": 0.1773470938205719, |
|
"eval_runtime": 582.2966, |
|
"eval_samples_per_second": 25.913, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0406722627603737, |
|
"step": 30300 |
|
}, |
|
{ |
|
"epoch": 5.5, |
|
"eval_loss": 0.1722005307674408, |
|
"eval_runtime": 580.9789, |
|
"eval_samples_per_second": 25.972, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0488530446285425, |
|
"step": 30400 |
|
}, |
|
{ |
|
"epoch": 5.52, |
|
"learning_rate": 0.00019084324193156997, |
|
"loss": 0.1276, |
|
"step": 30500 |
|
}, |
|
{ |
|
"epoch": 5.52, |
|
"eval_loss": 0.1720392405986786, |
|
"eval_runtime": 582.1568, |
|
"eval_samples_per_second": 25.919, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0520168492407478, |
|
"step": 30500 |
|
}, |
|
{ |
|
"epoch": 5.54, |
|
"eval_loss": 0.1776796579360962, |
|
"eval_runtime": 582.2358, |
|
"eval_samples_per_second": 25.916, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0346616435934481, |
|
"step": 30600 |
|
}, |
|
{ |
|
"epoch": 5.55, |
|
"eval_loss": 0.16850876808166504, |
|
"eval_runtime": 584.0539, |
|
"eval_samples_per_second": 25.835, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.03467993148138, |
|
"step": 30700 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"eval_loss": 0.16591408848762512, |
|
"eval_runtime": 583.1779, |
|
"eval_samples_per_second": 25.874, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0338082088232963, |
|
"step": 30800 |
|
}, |
|
{ |
|
"epoch": 5.59, |
|
"eval_loss": 0.17562197148799896, |
|
"eval_runtime": 585.3902, |
|
"eval_samples_per_second": 25.776, |
|
"eval_steps_per_second": 3.223, |
|
"eval_wer": 1.0228232841389149, |
|
"step": 30900 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 0.0001890232953166707, |
|
"loss": 0.1246, |
|
"step": 31000 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"eval_loss": 0.1716947704553604, |
|
"eval_runtime": 580.9184, |
|
"eval_samples_per_second": 25.974, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.040855141639692, |
|
"step": 31000 |
|
}, |
|
{ |
|
"epoch": 5.63, |
|
"eval_loss": 0.17640528082847595, |
|
"eval_runtime": 581.1871, |
|
"eval_samples_per_second": 25.962, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0201654444261565, |
|
"step": 31100 |
|
}, |
|
{ |
|
"epoch": 5.64, |
|
"eval_loss": 0.16931375861167908, |
|
"eval_runtime": 582.1998, |
|
"eval_samples_per_second": 25.917, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0314368793548032, |
|
"step": 31200 |
|
}, |
|
{ |
|
"epoch": 5.66, |
|
"eval_loss": 0.17311854660511017, |
|
"eval_runtime": 581.8005, |
|
"eval_samples_per_second": 25.935, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0319184604036746, |
|
"step": 31300 |
|
}, |
|
{ |
|
"epoch": 5.68, |
|
"eval_loss": 0.16878977417945862, |
|
"eval_runtime": 580.1048, |
|
"eval_samples_per_second": 26.011, |
|
"eval_steps_per_second": 3.253, |
|
"eval_wer": 1.0380388068981914, |
|
"step": 31400 |
|
}, |
|
{ |
|
"epoch": 5.7, |
|
"learning_rate": 0.00018720334870177139, |
|
"loss": 0.1271, |
|
"step": 31500 |
|
}, |
|
{ |
|
"epoch": 5.7, |
|
"eval_loss": 0.16712072491645813, |
|
"eval_runtime": 580.9082, |
|
"eval_samples_per_second": 25.975, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0349908255762208, |
|
"step": 31500 |
|
}, |
|
{ |
|
"epoch": 5.72, |
|
"eval_loss": 0.1675543487071991, |
|
"eval_runtime": 581.5005, |
|
"eval_samples_per_second": 25.948, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.043025304340935, |
|
"step": 31600 |
|
}, |
|
{ |
|
"epoch": 5.73, |
|
"eval_loss": 0.16557875275611877, |
|
"eval_runtime": 592.5273, |
|
"eval_samples_per_second": 25.465, |
|
"eval_steps_per_second": 3.185, |
|
"eval_wer": 1.0440738099156928, |
|
"step": 31700 |
|
}, |
|
{ |
|
"epoch": 5.75, |
|
"eval_loss": 0.16642601788043976, |
|
"eval_runtime": 582.1063, |
|
"eval_samples_per_second": 25.921, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0403126009643813, |
|
"step": 31800 |
|
}, |
|
{ |
|
"epoch": 5.77, |
|
"eval_loss": 0.16907727718353271, |
|
"eval_runtime": 581.4123, |
|
"eval_samples_per_second": 25.952, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.015185042946057, |
|
"step": 31900 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 0.0001853834020868721, |
|
"loss": 0.1259, |
|
"step": 32000 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"eval_loss": 0.17020300030708313, |
|
"eval_runtime": 581.9961, |
|
"eval_samples_per_second": 25.926, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0017556372414549, |
|
"step": 32000 |
|
}, |
|
{ |
|
"epoch": 5.81, |
|
"eval_loss": 0.16643249988555908, |
|
"eval_runtime": 580.5409, |
|
"eval_samples_per_second": 25.991, |
|
"eval_steps_per_second": 3.25, |
|
"eval_wer": 1.024554537529794, |
|
"step": 32100 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"eval_loss": 0.17374736070632935, |
|
"eval_runtime": 581.8721, |
|
"eval_samples_per_second": 25.932, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0339545119267508, |
|
"step": 32200 |
|
}, |
|
{ |
|
"epoch": 5.84, |
|
"eval_loss": 0.17424912750720978, |
|
"eval_runtime": 581.9636, |
|
"eval_samples_per_second": 25.928, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0448906689099808, |
|
"step": 32300 |
|
}, |
|
{ |
|
"epoch": 5.86, |
|
"eval_loss": 0.170697420835495, |
|
"eval_runtime": 581.919, |
|
"eval_samples_per_second": 25.93, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0279012210213176, |
|
"step": 32400 |
|
}, |
|
{ |
|
"epoch": 5.88, |
|
"learning_rate": 0.0001835634554719728, |
|
"loss": 0.1273, |
|
"step": 32500 |
|
}, |
|
{ |
|
"epoch": 5.88, |
|
"eval_loss": 0.16966979205608368, |
|
"eval_runtime": 573.0944, |
|
"eval_samples_per_second": 26.329, |
|
"eval_steps_per_second": 3.293, |
|
"eval_wer": 1.0470852154617996, |
|
"step": 32500 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"eval_loss": 0.16675007343292236, |
|
"eval_runtime": 583.4412, |
|
"eval_samples_per_second": 25.862, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.0322171625732277, |
|
"step": 32600 |
|
}, |
|
{ |
|
"epoch": 5.92, |
|
"eval_loss": 0.17055776715278625, |
|
"eval_runtime": 582.1651, |
|
"eval_samples_per_second": 25.919, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.037782776467146, |
|
"step": 32700 |
|
}, |
|
{ |
|
"epoch": 5.93, |
|
"eval_loss": 0.17042866349220276, |
|
"eval_runtime": 582.8815, |
|
"eval_samples_per_second": 25.887, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0350274013520846, |
|
"step": 32800 |
|
}, |
|
{ |
|
"epoch": 5.95, |
|
"eval_loss": 0.17252954840660095, |
|
"eval_runtime": 583.3586, |
|
"eval_samples_per_second": 25.866, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0244021384636954, |
|
"step": 32900 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 0.00018174350885707353, |
|
"loss": 0.123, |
|
"step": 33000 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"eval_loss": 0.16781975328922272, |
|
"eval_runtime": 581.176, |
|
"eval_samples_per_second": 25.963, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.044683406180087, |
|
"step": 33000 |
|
}, |
|
{ |
|
"epoch": 5.99, |
|
"eval_loss": 0.1680649071931839, |
|
"eval_runtime": 583.9517, |
|
"eval_samples_per_second": 25.839, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0438177794846473, |
|
"step": 33100 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"eval_loss": 0.16894467175006866, |
|
"eval_runtime": 582.6025, |
|
"eval_samples_per_second": 25.899, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0297117219265681, |
|
"step": 33200 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"eval_loss": 0.1690208464860916, |
|
"eval_runtime": 582.3983, |
|
"eval_samples_per_second": 25.908, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0333388196997129, |
|
"step": 33300 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"eval_loss": 0.173419788479805, |
|
"eval_runtime": 582.2669, |
|
"eval_samples_per_second": 25.914, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0296324744121967, |
|
"step": 33400 |
|
}, |
|
{ |
|
"epoch": 6.06, |
|
"learning_rate": 0.00017992356224217422, |
|
"loss": 0.1163, |
|
"step": 33500 |
|
}, |
|
{ |
|
"epoch": 6.06, |
|
"eval_loss": 0.1748138964176178, |
|
"eval_runtime": 582.5758, |
|
"eval_samples_per_second": 25.9, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.03073584365075, |
|
"step": 33500 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"eval_loss": 0.17153716087341309, |
|
"eval_runtime": 588.9678, |
|
"eval_samples_per_second": 25.619, |
|
"eval_steps_per_second": 3.204, |
|
"eval_wer": 1.0122528849143213, |
|
"step": 33600 |
|
}, |
|
{ |
|
"epoch": 6.1, |
|
"eval_loss": 0.16684116423130035, |
|
"eval_runtime": 581.9585, |
|
"eval_samples_per_second": 25.928, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.011655480575215, |
|
"step": 33700 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"eval_loss": 0.1689983457326889, |
|
"eval_runtime": 580.6755, |
|
"eval_samples_per_second": 25.985, |
|
"eval_steps_per_second": 3.25, |
|
"eval_wer": 1.0229634912797254, |
|
"step": 33800 |
|
}, |
|
{ |
|
"epoch": 6.13, |
|
"eval_loss": 0.16927799582481384, |
|
"eval_runtime": 581.3775, |
|
"eval_samples_per_second": 25.954, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0165688264662314, |
|
"step": 33900 |
|
}, |
|
{ |
|
"epoch": 6.15, |
|
"learning_rate": 0.00017810361562727492, |
|
"loss": 0.1101, |
|
"step": 34000 |
|
}, |
|
{ |
|
"epoch": 6.15, |
|
"eval_loss": 0.17283213138580322, |
|
"eval_runtime": 581.7575, |
|
"eval_samples_per_second": 25.937, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0161664929317313, |
|
"step": 34000 |
|
}, |
|
{ |
|
"epoch": 6.17, |
|
"eval_loss": 0.16832078993320465, |
|
"eval_runtime": 593.7449, |
|
"eval_samples_per_second": 25.413, |
|
"eval_steps_per_second": 3.178, |
|
"eval_wer": 1.0107167023280481, |
|
"step": 34100 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"eval_loss": 0.17034588754177094, |
|
"eval_runtime": 581.571, |
|
"eval_samples_per_second": 25.945, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 0.9813646421974727, |
|
"step": 34200 |
|
}, |
|
{ |
|
"epoch": 6.2, |
|
"eval_loss": 0.16915497183799744, |
|
"eval_runtime": 584.1319, |
|
"eval_samples_per_second": 25.831, |
|
"eval_steps_per_second": 3.23, |
|
"eval_wer": 1.0007437074425607, |
|
"step": 34300 |
|
}, |
|
{ |
|
"epoch": 6.22, |
|
"eval_loss": 0.16902200877666473, |
|
"eval_runtime": 579.9055, |
|
"eval_samples_per_second": 26.02, |
|
"eval_steps_per_second": 3.254, |
|
"eval_wer": 0.9999695201867803, |
|
"step": 34400 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 0.00017629094879883522, |
|
"loss": 0.1118, |
|
"step": 34500 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"eval_loss": 0.1733812838792801, |
|
"eval_runtime": 641.6204, |
|
"eval_samples_per_second": 23.517, |
|
"eval_steps_per_second": 2.941, |
|
"eval_wer": 0.9971958571837872, |
|
"step": 34500 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"eval_loss": 0.17394082248210907, |
|
"eval_runtime": 583.4185, |
|
"eval_samples_per_second": 25.863, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.0096438129027145, |
|
"step": 34600 |
|
}, |
|
{ |
|
"epoch": 6.28, |
|
"eval_loss": 0.17487762868404388, |
|
"eval_runtime": 586.9087, |
|
"eval_samples_per_second": 25.709, |
|
"eval_steps_per_second": 3.215, |
|
"eval_wer": 1.0046695073852587, |
|
"step": 34700 |
|
}, |
|
{ |
|
"epoch": 6.3, |
|
"eval_loss": 0.17093946039676666, |
|
"eval_runtime": 647.3178, |
|
"eval_samples_per_second": 23.31, |
|
"eval_steps_per_second": 2.915, |
|
"eval_wer": 1.0111068439372604, |
|
"step": 34800 |
|
}, |
|
{ |
|
"epoch": 6.31, |
|
"eval_loss": 0.17170192301273346, |
|
"eval_runtime": 816.7662, |
|
"eval_samples_per_second": 18.474, |
|
"eval_steps_per_second": 2.31, |
|
"eval_wer": 1.0179038422852544, |
|
"step": 34900 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 0.00017447100218393594, |
|
"loss": 0.1153, |
|
"step": 35000 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"eval_loss": 0.16898946464061737, |
|
"eval_runtime": 581.8044, |
|
"eval_samples_per_second": 25.935, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0155142249288296, |
|
"step": 35000 |
|
}, |
|
{ |
|
"epoch": 6.35, |
|
"eval_loss": 0.17097432911396027, |
|
"eval_runtime": 580.1808, |
|
"eval_samples_per_second": 26.007, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0143803758770567, |
|
"step": 35100 |
|
}, |
|
{ |
|
"epoch": 6.37, |
|
"eval_loss": 0.1719246357679367, |
|
"eval_runtime": 580.9111, |
|
"eval_samples_per_second": 25.975, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0030418853593266, |
|
"step": 35200 |
|
}, |
|
{ |
|
"epoch": 6.39, |
|
"eval_loss": 0.1690385490655899, |
|
"eval_runtime": 650.929, |
|
"eval_samples_per_second": 23.181, |
|
"eval_steps_per_second": 2.899, |
|
"eval_wer": 1.02722456916784, |
|
"step": 35300 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"eval_loss": 0.16729648411273956, |
|
"eval_runtime": 581.1582, |
|
"eval_samples_per_second": 25.964, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0103387526441239, |
|
"step": 35400 |
|
}, |
|
{ |
|
"epoch": 6.42, |
|
"learning_rate": 0.00017265105556903663, |
|
"loss": 0.1106, |
|
"step": 35500 |
|
}, |
|
{ |
|
"epoch": 6.42, |
|
"eval_loss": 0.1710328310728073, |
|
"eval_runtime": 601.8486, |
|
"eval_samples_per_second": 25.071, |
|
"eval_steps_per_second": 3.135, |
|
"eval_wer": 1.0222136878745207, |
|
"step": 35500 |
|
}, |
|
{ |
|
"epoch": 6.44, |
|
"eval_loss": 0.17468269169330597, |
|
"eval_runtime": 590.7957, |
|
"eval_samples_per_second": 25.54, |
|
"eval_steps_per_second": 3.194, |
|
"eval_wer": 1.0172881500582165, |
|
"step": 35600 |
|
}, |
|
{ |
|
"epoch": 6.46, |
|
"eval_loss": 0.17207881808280945, |
|
"eval_runtime": 632.0801, |
|
"eval_samples_per_second": 23.872, |
|
"eval_steps_per_second": 2.985, |
|
"eval_wer": 0.9932578653158013, |
|
"step": 35700 |
|
}, |
|
{ |
|
"epoch": 6.48, |
|
"eval_loss": 0.1670292764902115, |
|
"eval_runtime": 582.7073, |
|
"eval_samples_per_second": 25.895, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.018354943520906, |
|
"step": 35800 |
|
}, |
|
{ |
|
"epoch": 6.49, |
|
"eval_loss": 0.17143051326274872, |
|
"eval_runtime": 594.2992, |
|
"eval_samples_per_second": 25.39, |
|
"eval_steps_per_second": 3.175, |
|
"eval_wer": 1.0122224051011015, |
|
"step": 35900 |
|
}, |
|
{ |
|
"epoch": 6.51, |
|
"learning_rate": 0.00017083110895413733, |
|
"loss": 0.1116, |
|
"step": 36000 |
|
}, |
|
{ |
|
"epoch": 6.51, |
|
"eval_loss": 0.17166104912757874, |
|
"eval_runtime": 581.3301, |
|
"eval_samples_per_second": 25.956, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0034929865949782, |
|
"step": 36000 |
|
}, |
|
{ |
|
"epoch": 6.53, |
|
"eval_loss": 0.16851219534873962, |
|
"eval_runtime": 794.8894, |
|
"eval_samples_per_second": 18.983, |
|
"eval_steps_per_second": 2.374, |
|
"eval_wer": 1.009893747371116, |
|
"step": 36100 |
|
}, |
|
{ |
|
"epoch": 6.55, |
|
"eval_loss": 0.16873739659786224, |
|
"eval_runtime": 642.5817, |
|
"eval_samples_per_second": 23.482, |
|
"eval_steps_per_second": 2.937, |
|
"eval_wer": 1.0288217113805527, |
|
"step": 36200 |
|
}, |
|
{ |
|
"epoch": 6.57, |
|
"eval_loss": 0.16639259457588196, |
|
"eval_runtime": 582.0547, |
|
"eval_samples_per_second": 25.924, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0313881116536519, |
|
"step": 36300 |
|
}, |
|
{ |
|
"epoch": 6.58, |
|
"eval_loss": 0.16646970808506012, |
|
"eval_runtime": 581.4585, |
|
"eval_samples_per_second": 25.95, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0263589424724004, |
|
"step": 36400 |
|
}, |
|
{ |
|
"epoch": 6.6, |
|
"learning_rate": 0.00016901116233923805, |
|
"loss": 0.1128, |
|
"step": 36500 |
|
}, |
|
{ |
|
"epoch": 6.6, |
|
"eval_loss": 0.16809915006160736, |
|
"eval_runtime": 841.9975, |
|
"eval_samples_per_second": 17.92, |
|
"eval_steps_per_second": 2.241, |
|
"eval_wer": 1.041995086654109, |
|
"step": 36500 |
|
}, |
|
{ |
|
"epoch": 6.62, |
|
"eval_loss": 0.1682288646697998, |
|
"eval_runtime": 581.315, |
|
"eval_samples_per_second": 25.957, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0408856214529116, |
|
"step": 36600 |
|
}, |
|
{ |
|
"epoch": 6.64, |
|
"eval_loss": 0.17166656255722046, |
|
"eval_runtime": 596.6613, |
|
"eval_samples_per_second": 25.289, |
|
"eval_steps_per_second": 3.163, |
|
"eval_wer": 1.0270538822138098, |
|
"step": 36700 |
|
}, |
|
{ |
|
"epoch": 6.66, |
|
"eval_loss": 0.17169848084449768, |
|
"eval_runtime": 580.5042, |
|
"eval_samples_per_second": 25.993, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0165993062794512, |
|
"step": 36800 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"eval_loss": 0.1754983514547348, |
|
"eval_runtime": 667.9005, |
|
"eval_samples_per_second": 22.592, |
|
"eval_steps_per_second": 2.825, |
|
"eval_wer": 1.0174527410496028, |
|
"step": 36900 |
|
}, |
|
{ |
|
"epoch": 6.69, |
|
"learning_rate": 0.00016719121572433872, |
|
"loss": 0.1134, |
|
"step": 37000 |
|
}, |
|
{ |
|
"epoch": 6.69, |
|
"eval_loss": 0.16234032809734344, |
|
"eval_runtime": 661.7885, |
|
"eval_samples_per_second": 22.8, |
|
"eval_steps_per_second": 2.851, |
|
"eval_wer": 1.0185012466243606, |
|
"step": 37000 |
|
}, |
|
{ |
|
"epoch": 6.71, |
|
"eval_loss": 0.16741453111171722, |
|
"eval_runtime": 591.6954, |
|
"eval_samples_per_second": 25.501, |
|
"eval_steps_per_second": 3.189, |
|
"eval_wer": 1.0301811110501515, |
|
"step": 37100 |
|
}, |
|
{ |
|
"epoch": 6.73, |
|
"eval_loss": 0.16326996684074402, |
|
"eval_runtime": 606.6342, |
|
"eval_samples_per_second": 24.873, |
|
"eval_steps_per_second": 3.111, |
|
"eval_wer": 1.0324670970416294, |
|
"step": 37200 |
|
}, |
|
{ |
|
"epoch": 6.75, |
|
"eval_loss": 0.1627754420042038, |
|
"eval_runtime": 925.563, |
|
"eval_samples_per_second": 16.303, |
|
"eval_steps_per_second": 2.039, |
|
"eval_wer": 1.0228171881762709, |
|
"step": 37300 |
|
}, |
|
{ |
|
"epoch": 6.77, |
|
"eval_loss": 0.16362273693084717, |
|
"eval_runtime": 699.1407, |
|
"eval_samples_per_second": 21.582, |
|
"eval_steps_per_second": 2.699, |
|
"eval_wer": 1.024261931322885, |
|
"step": 37400 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"learning_rate": 0.00016537126910943944, |
|
"loss": 0.1102, |
|
"step": 37500 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"eval_loss": 0.16669456660747528, |
|
"eval_runtime": 583.9747, |
|
"eval_samples_per_second": 25.838, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0282304030040903, |
|
"step": 37500 |
|
}, |
|
{ |
|
"epoch": 6.8, |
|
"eval_loss": 0.16227515041828156, |
|
"eval_runtime": 588.9317, |
|
"eval_samples_per_second": 25.621, |
|
"eval_steps_per_second": 3.204, |
|
"eval_wer": 1.0212078540382705, |
|
"step": 37600 |
|
}, |
|
{ |
|
"epoch": 6.82, |
|
"eval_loss": 0.1639271229505539, |
|
"eval_runtime": 594.657, |
|
"eval_samples_per_second": 25.374, |
|
"eval_steps_per_second": 3.173, |
|
"eval_wer": 1.0139536584919808, |
|
"step": 37700 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"eval_loss": 0.15872186422348022, |
|
"eval_runtime": 632.8508, |
|
"eval_samples_per_second": 23.843, |
|
"eval_steps_per_second": 2.982, |
|
"eval_wer": 1.0258285937223777, |
|
"step": 37800 |
|
}, |
|
{ |
|
"epoch": 6.86, |
|
"eval_loss": 0.16100141406059265, |
|
"eval_runtime": 983.2839, |
|
"eval_samples_per_second": 15.346, |
|
"eval_steps_per_second": 1.919, |
|
"eval_wer": 1.0087050346555477, |
|
"step": 37900 |
|
}, |
|
{ |
|
"epoch": 6.87, |
|
"learning_rate": 0.00016355132249454014, |
|
"loss": 0.1113, |
|
"step": 38000 |
|
}, |
|
{ |
|
"epoch": 6.87, |
|
"eval_loss": 0.1646973341703415, |
|
"eval_runtime": 599.5992, |
|
"eval_samples_per_second": 25.165, |
|
"eval_steps_per_second": 3.147, |
|
"eval_wer": 1.0199277018830428, |
|
"step": 38000 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"eval_loss": 0.16088496148586273, |
|
"eval_runtime": 1148.6193, |
|
"eval_samples_per_second": 13.137, |
|
"eval_steps_per_second": 1.643, |
|
"eval_wer": 1.005364447126668, |
|
"step": 38100 |
|
}, |
|
{ |
|
"epoch": 6.91, |
|
"eval_loss": 0.16020412743091583, |
|
"eval_runtime": 638.6985, |
|
"eval_samples_per_second": 23.625, |
|
"eval_steps_per_second": 2.954, |
|
"eval_wer": 1.0145205830178672, |
|
"step": 38200 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"eval_loss": 0.16017159819602966, |
|
"eval_runtime": 590.1313, |
|
"eval_samples_per_second": 25.569, |
|
"eval_steps_per_second": 3.198, |
|
"eval_wer": 1.014435239540852, |
|
"step": 38300 |
|
}, |
|
{ |
|
"epoch": 6.95, |
|
"eval_loss": 0.16017083823680878, |
|
"eval_runtime": 583.7731, |
|
"eval_samples_per_second": 25.847, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0374840742975926, |
|
"step": 38400 |
|
}, |
|
{ |
|
"epoch": 6.96, |
|
"learning_rate": 0.00016173137587964084, |
|
"loss": 0.1071, |
|
"step": 38500 |
|
}, |
|
{ |
|
"epoch": 6.96, |
|
"eval_loss": 0.15924811363220215, |
|
"eval_runtime": 644.5353, |
|
"eval_samples_per_second": 23.411, |
|
"eval_steps_per_second": 2.928, |
|
"eval_wer": 1.0259261291246806, |
|
"step": 38500 |
|
}, |
|
{ |
|
"epoch": 6.98, |
|
"eval_loss": 0.16121791303157806, |
|
"eval_runtime": 583.6652, |
|
"eval_samples_per_second": 25.852, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.0235608956188316, |
|
"step": 38600 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.16208681464195251, |
|
"eval_runtime": 586.5854, |
|
"eval_samples_per_second": 25.723, |
|
"eval_steps_per_second": 3.217, |
|
"eval_wer": 1.0276695744408477, |
|
"step": 38700 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"eval_loss": 0.1668541133403778, |
|
"eval_runtime": 583.1032, |
|
"eval_samples_per_second": 25.877, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0367281749297441, |
|
"step": 38800 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"eval_loss": 0.17419211566448212, |
|
"eval_runtime": 647.5268, |
|
"eval_samples_per_second": 23.303, |
|
"eval_steps_per_second": 2.914, |
|
"eval_wer": 1.0484324232061106, |
|
"step": 38900 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 0.00015991142926474156, |
|
"loss": 0.1062, |
|
"step": 39000 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"eval_loss": 0.17524433135986328, |
|
"eval_runtime": 582.9109, |
|
"eval_samples_per_second": 25.886, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0301567271995757, |
|
"step": 39000 |
|
}, |
|
{ |
|
"epoch": 7.07, |
|
"eval_loss": 0.16763833165168762, |
|
"eval_runtime": 832.1716, |
|
"eval_samples_per_second": 18.132, |
|
"eval_steps_per_second": 2.268, |
|
"eval_wer": 1.024444810202203, |
|
"step": 39100 |
|
}, |
|
{ |
|
"epoch": 7.09, |
|
"eval_loss": 0.17226064205169678, |
|
"eval_runtime": 584.5325, |
|
"eval_samples_per_second": 25.814, |
|
"eval_steps_per_second": 3.228, |
|
"eval_wer": 1.0300104240961212, |
|
"step": 39200 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"eval_loss": 0.1727043092250824, |
|
"eval_runtime": 732.8624, |
|
"eval_samples_per_second": 20.589, |
|
"eval_steps_per_second": 2.575, |
|
"eval_wer": 1.0293886359064393, |
|
"step": 39300 |
|
}, |
|
{ |
|
"epoch": 7.13, |
|
"eval_loss": 0.17107614874839783, |
|
"eval_runtime": 583.7282, |
|
"eval_samples_per_second": 25.849, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.025475027889029, |
|
"step": 39400 |
|
}, |
|
{ |
|
"epoch": 7.15, |
|
"learning_rate": 0.00015809512254307204, |
|
"loss": 0.1021, |
|
"step": 39500 |
|
}, |
|
{ |
|
"epoch": 7.15, |
|
"eval_loss": 0.16992105543613434, |
|
"eval_runtime": 585.4315, |
|
"eval_samples_per_second": 25.774, |
|
"eval_steps_per_second": 3.223, |
|
"eval_wer": 1.0471156952750194, |
|
"step": 39500 |
|
}, |
|
{ |
|
"epoch": 7.16, |
|
"eval_loss": 0.1682046800851822, |
|
"eval_runtime": 583.7765, |
|
"eval_samples_per_second": 25.847, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0425742031052834, |
|
"step": 39600 |
|
}, |
|
{ |
|
"epoch": 7.18, |
|
"eval_loss": 0.17128342390060425, |
|
"eval_runtime": 681.9553, |
|
"eval_samples_per_second": 22.126, |
|
"eval_steps_per_second": 2.767, |
|
"eval_wer": 1.0233353450010059, |
|
"step": 39700 |
|
}, |
|
{ |
|
"epoch": 7.2, |
|
"eval_loss": 0.16821503639221191, |
|
"eval_runtime": 662.0353, |
|
"eval_samples_per_second": 22.792, |
|
"eval_steps_per_second": 2.85, |
|
"eval_wer": 1.0259139371993928, |
|
"step": 39800 |
|
}, |
|
{ |
|
"epoch": 7.22, |
|
"eval_loss": 0.17101679742336273, |
|
"eval_runtime": 602.057, |
|
"eval_samples_per_second": 25.062, |
|
"eval_steps_per_second": 3.134, |
|
"eval_wer": 1.0161725888943753, |
|
"step": 39900 |
|
}, |
|
{ |
|
"epoch": 7.24, |
|
"learning_rate": 0.00015627881582140255, |
|
"loss": 0.103, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 7.24, |
|
"eval_loss": 0.17253848910331726, |
|
"eval_runtime": 585.651, |
|
"eval_samples_per_second": 25.764, |
|
"eval_steps_per_second": 3.222, |
|
"eval_wer": 1.0282730747425979, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"eval_loss": 0.1728762835264206, |
|
"eval_runtime": 997.1851, |
|
"eval_samples_per_second": 15.132, |
|
"eval_steps_per_second": 1.892, |
|
"eval_wer": 1.0263650384350445, |
|
"step": 40100 |
|
}, |
|
{ |
|
"epoch": 7.27, |
|
"eval_loss": 0.16648218035697937, |
|
"eval_runtime": 648.7615, |
|
"eval_samples_per_second": 23.258, |
|
"eval_steps_per_second": 2.909, |
|
"eval_wer": 1.045085739714587, |
|
"step": 40200 |
|
}, |
|
{ |
|
"epoch": 7.29, |
|
"eval_loss": 0.16705408692359924, |
|
"eval_runtime": 587.011, |
|
"eval_samples_per_second": 25.705, |
|
"eval_steps_per_second": 3.215, |
|
"eval_wer": 1.0386179233493658, |
|
"step": 40300 |
|
}, |
|
{ |
|
"epoch": 7.31, |
|
"eval_loss": 0.1670595407485962, |
|
"eval_runtime": 581.7984, |
|
"eval_samples_per_second": 25.935, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0316014703461898, |
|
"step": 40400 |
|
}, |
|
{ |
|
"epoch": 7.33, |
|
"learning_rate": 0.00015445886920650325, |
|
"loss": 0.0981, |
|
"step": 40500 |
|
}, |
|
{ |
|
"epoch": 7.33, |
|
"eval_loss": 0.17082154750823975, |
|
"eval_runtime": 644.8212, |
|
"eval_samples_per_second": 23.4, |
|
"eval_steps_per_second": 2.926, |
|
"eval_wer": 1.0256761946562791, |
|
"step": 40500 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"eval_loss": 0.16420403122901917, |
|
"eval_runtime": 584.3525, |
|
"eval_samples_per_second": 25.822, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.0152033308339887, |
|
"step": 40600 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"eval_loss": 0.1707213968038559, |
|
"eval_runtime": 598.9814, |
|
"eval_samples_per_second": 25.191, |
|
"eval_steps_per_second": 3.15, |
|
"eval_wer": 1.0110215004602452, |
|
"step": 40700 |
|
}, |
|
{ |
|
"epoch": 7.38, |
|
"eval_loss": 0.1675441563129425, |
|
"eval_runtime": 586.7024, |
|
"eval_samples_per_second": 25.718, |
|
"eval_steps_per_second": 3.216, |
|
"eval_wer": 1.0185561102881562, |
|
"step": 40800 |
|
}, |
|
{ |
|
"epoch": 7.4, |
|
"eval_loss": 0.17023596167564392, |
|
"eval_runtime": 713.0578, |
|
"eval_samples_per_second": 21.161, |
|
"eval_steps_per_second": 2.646, |
|
"eval_wer": 1.012277268764897, |
|
"step": 40900 |
|
}, |
|
{ |
|
"epoch": 7.42, |
|
"learning_rate": 0.00015263892259160397, |
|
"loss": 0.1005, |
|
"step": 41000 |
|
}, |
|
{ |
|
"epoch": 7.42, |
|
"eval_loss": 0.16991430521011353, |
|
"eval_runtime": 583.1849, |
|
"eval_samples_per_second": 25.873, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0159287503886176, |
|
"step": 41000 |
|
}, |
|
{ |
|
"epoch": 7.43, |
|
"eval_loss": 0.1702755093574524, |
|
"eval_runtime": 586.1073, |
|
"eval_samples_per_second": 25.744, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.0219271776302554, |
|
"step": 41100 |
|
}, |
|
{ |
|
"epoch": 7.45, |
|
"eval_loss": 0.17067919671535492, |
|
"eval_runtime": 588.7524, |
|
"eval_samples_per_second": 25.629, |
|
"eval_steps_per_second": 3.205, |
|
"eval_wer": 1.019385161207732, |
|
"step": 41200 |
|
}, |
|
{ |
|
"epoch": 7.47, |
|
"eval_loss": 0.16438345611095428, |
|
"eval_runtime": 813.104, |
|
"eval_samples_per_second": 18.557, |
|
"eval_steps_per_second": 2.321, |
|
"eval_wer": 1.0016215260632884, |
|
"step": 41300 |
|
}, |
|
{ |
|
"epoch": 7.49, |
|
"eval_loss": 0.17156347632408142, |
|
"eval_runtime": 608.2034, |
|
"eval_samples_per_second": 24.809, |
|
"eval_steps_per_second": 3.103, |
|
"eval_wer": 0.9941478758618167, |
|
"step": 41400 |
|
}, |
|
{ |
|
"epoch": 7.51, |
|
"learning_rate": 0.00015081897597670466, |
|
"loss": 0.1021, |
|
"step": 41500 |
|
}, |
|
{ |
|
"epoch": 7.51, |
|
"eval_loss": 0.16701160371303558, |
|
"eval_runtime": 580.9378, |
|
"eval_samples_per_second": 25.974, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0159470382765494, |
|
"step": 41500 |
|
}, |
|
{ |
|
"epoch": 7.53, |
|
"eval_loss": 0.16667711734771729, |
|
"eval_runtime": 580.8947, |
|
"eval_samples_per_second": 25.975, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.003291819827728, |
|
"step": 41600 |
|
}, |
|
{ |
|
"epoch": 7.54, |
|
"eval_loss": 0.1667308658361435, |
|
"eval_runtime": 738.8402, |
|
"eval_samples_per_second": 20.423, |
|
"eval_steps_per_second": 2.554, |
|
"eval_wer": 1.0175624683771938, |
|
"step": 41700 |
|
}, |
|
{ |
|
"epoch": 7.56, |
|
"eval_loss": 0.16792383790016174, |
|
"eval_runtime": 721.671, |
|
"eval_samples_per_second": 20.908, |
|
"eval_steps_per_second": 2.615, |
|
"eval_wer": 1.0193790652450883, |
|
"step": 41800 |
|
}, |
|
{ |
|
"epoch": 7.58, |
|
"eval_loss": 0.1631632000207901, |
|
"eval_runtime": 591.7115, |
|
"eval_samples_per_second": 25.501, |
|
"eval_steps_per_second": 3.189, |
|
"eval_wer": 1.0418426875880105, |
|
"step": 41900 |
|
}, |
|
{ |
|
"epoch": 7.6, |
|
"learning_rate": 0.0001489990293618054, |
|
"loss": 0.0963, |
|
"step": 42000 |
|
}, |
|
{ |
|
"epoch": 7.6, |
|
"eval_loss": 0.17123085260391235, |
|
"eval_runtime": 592.0783, |
|
"eval_samples_per_second": 25.485, |
|
"eval_steps_per_second": 3.187, |
|
"eval_wer": 1.0152399066098523, |
|
"step": 42000 |
|
}, |
|
{ |
|
"epoch": 7.62, |
|
"eval_loss": 0.16319897770881653, |
|
"eval_runtime": 838.4842, |
|
"eval_samples_per_second": 17.996, |
|
"eval_steps_per_second": 2.25, |
|
"eval_wer": 1.0364477606481228, |
|
"step": 42100 |
|
}, |
|
{ |
|
"epoch": 7.63, |
|
"eval_loss": 0.17024168372154236, |
|
"eval_runtime": 1184.0841, |
|
"eval_samples_per_second": 12.743, |
|
"eval_steps_per_second": 1.594, |
|
"eval_wer": 1.0228598599147785, |
|
"step": 42200 |
|
}, |
|
{ |
|
"epoch": 7.65, |
|
"eval_loss": 0.1655167192220688, |
|
"eval_runtime": 581.3081, |
|
"eval_samples_per_second": 25.957, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0178733624720349, |
|
"step": 42300 |
|
}, |
|
{ |
|
"epoch": 7.67, |
|
"eval_loss": 0.16978418827056885, |
|
"eval_runtime": 580.4103, |
|
"eval_samples_per_second": 25.997, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0329425821278566, |
|
"step": 42400 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"learning_rate": 0.00014717908274690608, |
|
"loss": 0.1014, |
|
"step": 42500 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"eval_loss": 0.1691199243068695, |
|
"eval_runtime": 715.0503, |
|
"eval_samples_per_second": 21.102, |
|
"eval_steps_per_second": 2.639, |
|
"eval_wer": 1.0398432118407979, |
|
"step": 42500 |
|
}, |
|
{ |
|
"epoch": 7.71, |
|
"eval_loss": 0.1637689173221588, |
|
"eval_runtime": 790.6965, |
|
"eval_samples_per_second": 19.083, |
|
"eval_steps_per_second": 2.387, |
|
"eval_wer": 1.0486945495998001, |
|
"step": 42600 |
|
}, |
|
{ |
|
"epoch": 7.72, |
|
"eval_loss": 0.16167329251766205, |
|
"eval_runtime": 591.7835, |
|
"eval_samples_per_second": 25.497, |
|
"eval_steps_per_second": 3.189, |
|
"eval_wer": 1.0210066872710204, |
|
"step": 42700 |
|
}, |
|
{ |
|
"epoch": 7.74, |
|
"eval_loss": 0.1647609919309616, |
|
"eval_runtime": 595.5162, |
|
"eval_samples_per_second": 25.338, |
|
"eval_steps_per_second": 3.169, |
|
"eval_wer": 1.0123504203166243, |
|
"step": 42800 |
|
}, |
|
{ |
|
"epoch": 7.76, |
|
"eval_loss": 0.16076742112636566, |
|
"eval_runtime": 849.0674, |
|
"eval_samples_per_second": 17.771, |
|
"eval_steps_per_second": 2.222, |
|
"eval_wer": 1.0202142121273081, |
|
"step": 42900 |
|
}, |
|
{ |
|
"epoch": 7.78, |
|
"learning_rate": 0.00014535913613200678, |
|
"loss": 0.1008, |
|
"step": 43000 |
|
}, |
|
{ |
|
"epoch": 7.78, |
|
"eval_loss": 0.1611439436674118, |
|
"eval_runtime": 692.2883, |
|
"eval_samples_per_second": 21.796, |
|
"eval_steps_per_second": 2.726, |
|
"eval_wer": 1.0353261035216377, |
|
"step": 43000 |
|
}, |
|
{ |
|
"epoch": 7.8, |
|
"eval_loss": 0.16334283351898193, |
|
"eval_runtime": 587.0659, |
|
"eval_samples_per_second": 25.702, |
|
"eval_steps_per_second": 3.214, |
|
"eval_wer": 1.0319123644410306, |
|
"step": 43100 |
|
}, |
|
{ |
|
"epoch": 7.81, |
|
"eval_loss": 0.16403447091579437, |
|
"eval_runtime": 603.3209, |
|
"eval_samples_per_second": 25.01, |
|
"eval_steps_per_second": 3.128, |
|
"eval_wer": 1.0031577086495613, |
|
"step": 43200 |
|
}, |
|
{ |
|
"epoch": 7.83, |
|
"eval_loss": 0.15894734859466553, |
|
"eval_runtime": 900.4737, |
|
"eval_samples_per_second": 16.757, |
|
"eval_steps_per_second": 2.096, |
|
"eval_wer": 0.9984821053016587, |
|
"step": 43300 |
|
}, |
|
{ |
|
"epoch": 7.85, |
|
"eval_loss": 0.16296441853046417, |
|
"eval_runtime": 734.1091, |
|
"eval_samples_per_second": 20.554, |
|
"eval_steps_per_second": 2.57, |
|
"eval_wer": 0.9975372310918479, |
|
"step": 43400 |
|
}, |
|
{ |
|
"epoch": 7.87, |
|
"learning_rate": 0.00014353918951710747, |
|
"loss": 0.0988, |
|
"step": 43500 |
|
}, |
|
{ |
|
"epoch": 7.87, |
|
"eval_loss": 0.16040995717048645, |
|
"eval_runtime": 597.3861, |
|
"eval_samples_per_second": 25.258, |
|
"eval_steps_per_second": 3.159, |
|
"eval_wer": 1.0053156794255165, |
|
"step": 43500 |
|
}, |
|
{ |
|
"epoch": 7.89, |
|
"eval_loss": 0.16874484717845917, |
|
"eval_runtime": 595.203, |
|
"eval_samples_per_second": 25.351, |
|
"eval_steps_per_second": 3.17, |
|
"eval_wer": 1.0063458971123425, |
|
"step": 43600 |
|
}, |
|
{ |
|
"epoch": 7.91, |
|
"eval_loss": 0.1619204580783844, |
|
"eval_runtime": 833.6968, |
|
"eval_samples_per_second": 18.099, |
|
"eval_steps_per_second": 2.263, |
|
"eval_wer": 1.0096377169400705, |
|
"step": 43700 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"eval_loss": 0.15647700428962708, |
|
"eval_runtime": 714.5224, |
|
"eval_samples_per_second": 21.118, |
|
"eval_steps_per_second": 2.641, |
|
"eval_wer": 0.99010015666624, |
|
"step": 43800 |
|
}, |
|
{ |
|
"epoch": 7.94, |
|
"eval_loss": 0.1618899703025818, |
|
"eval_runtime": 600.3451, |
|
"eval_samples_per_second": 25.134, |
|
"eval_steps_per_second": 3.143, |
|
"eval_wer": 0.9742140780161299, |
|
"step": 43900 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 0.00014172288279543798, |
|
"loss": 0.102, |
|
"step": 44000 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"eval_loss": 0.15979322791099548, |
|
"eval_runtime": 581.3117, |
|
"eval_samples_per_second": 25.957, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 0.9592789695384747, |
|
"step": 44000 |
|
}, |
|
{ |
|
"epoch": 7.98, |
|
"eval_loss": 0.16352316737174988, |
|
"eval_runtime": 701.4326, |
|
"eval_samples_per_second": 21.512, |
|
"eval_steps_per_second": 2.69, |
|
"eval_wer": 0.9717817889211975, |
|
"step": 44100 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.16242262721061707, |
|
"eval_runtime": 673.5202, |
|
"eval_samples_per_second": 22.403, |
|
"eval_steps_per_second": 2.802, |
|
"eval_wer": 0.9902769395829142, |
|
"step": 44200 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"eval_loss": 0.16053874790668488, |
|
"eval_runtime": 581.9167, |
|
"eval_samples_per_second": 25.93, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 0.9882043122839743, |
|
"step": 44300 |
|
}, |
|
{ |
|
"epoch": 8.03, |
|
"eval_loss": 0.1657256782054901, |
|
"eval_runtime": 580.7431, |
|
"eval_samples_per_second": 25.982, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.0128137134775639, |
|
"step": 44400 |
|
}, |
|
{ |
|
"epoch": 8.05, |
|
"learning_rate": 0.0001399065760737685, |
|
"loss": 0.0961, |
|
"step": 44500 |
|
}, |
|
{ |
|
"epoch": 8.05, |
|
"eval_loss": 0.1650768518447876, |
|
"eval_runtime": 757.4307, |
|
"eval_samples_per_second": 19.921, |
|
"eval_steps_per_second": 2.491, |
|
"eval_wer": 1.0154959370408978, |
|
"step": 44500 |
|
}, |
|
{ |
|
"epoch": 8.07, |
|
"eval_loss": 0.16800330579280853, |
|
"eval_runtime": 697.2243, |
|
"eval_samples_per_second": 21.642, |
|
"eval_steps_per_second": 2.706, |
|
"eval_wer": 1.0193546813945125, |
|
"step": 44600 |
|
}, |
|
{ |
|
"epoch": 8.09, |
|
"eval_loss": 0.16936592757701874, |
|
"eval_runtime": 580.6067, |
|
"eval_samples_per_second": 25.988, |
|
"eval_steps_per_second": 3.25, |
|
"eval_wer": 1.0111678035636997, |
|
"step": 44700 |
|
}, |
|
{ |
|
"epoch": 8.1, |
|
"eval_loss": 0.16645368933677673, |
|
"eval_runtime": 583.2116, |
|
"eval_samples_per_second": 25.872, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0072785793968655, |
|
"step": 44800 |
|
}, |
|
{ |
|
"epoch": 8.12, |
|
"eval_loss": 0.1612410545349121, |
|
"eval_runtime": 590.9695, |
|
"eval_samples_per_second": 25.533, |
|
"eval_steps_per_second": 3.193, |
|
"eval_wer": 1.020006949397414, |
|
"step": 44900 |
|
}, |
|
{ |
|
"epoch": 8.14, |
|
"learning_rate": 0.0001380866294588692, |
|
"loss": 0.0894, |
|
"step": 45000 |
|
}, |
|
{ |
|
"epoch": 8.14, |
|
"eval_loss": 0.1652226448059082, |
|
"eval_runtime": 627.3595, |
|
"eval_samples_per_second": 24.052, |
|
"eval_steps_per_second": 3.008, |
|
"eval_wer": 1.0336740976451297, |
|
"step": 45000 |
|
}, |
|
{ |
|
"epoch": 8.16, |
|
"eval_loss": 0.1626013070344925, |
|
"eval_runtime": 583.3577, |
|
"eval_samples_per_second": 25.866, |
|
"eval_steps_per_second": 3.235, |
|
"eval_wer": 1.0086257871411763, |
|
"step": 45100 |
|
}, |
|
{ |
|
"epoch": 8.18, |
|
"eval_loss": 0.16394564509391785, |
|
"eval_runtime": 708.5073, |
|
"eval_samples_per_second": 21.297, |
|
"eval_steps_per_second": 2.663, |
|
"eval_wer": 1.0083270849716233, |
|
"step": 45200 |
|
}, |
|
{ |
|
"epoch": 8.19, |
|
"eval_loss": 0.16342629492282867, |
|
"eval_runtime": 710.8612, |
|
"eval_samples_per_second": 21.226, |
|
"eval_steps_per_second": 2.655, |
|
"eval_wer": 1.0223356071273995, |
|
"step": 45300 |
|
}, |
|
{ |
|
"epoch": 8.21, |
|
"eval_loss": 0.16308727860450745, |
|
"eval_runtime": 586.3602, |
|
"eval_samples_per_second": 25.733, |
|
"eval_steps_per_second": 3.218, |
|
"eval_wer": 1.0339240321135312, |
|
"step": 45400 |
|
}, |
|
{ |
|
"epoch": 8.23, |
|
"learning_rate": 0.00013626668284396988, |
|
"loss": 0.0887, |
|
"step": 45500 |
|
}, |
|
{ |
|
"epoch": 8.23, |
|
"eval_loss": 0.163980633020401, |
|
"eval_runtime": 632.8729, |
|
"eval_samples_per_second": 23.842, |
|
"eval_steps_per_second": 2.982, |
|
"eval_wer": 1.0311076973720306, |
|
"step": 45500 |
|
}, |
|
{ |
|
"epoch": 8.25, |
|
"eval_loss": 0.16611836850643158, |
|
"eval_runtime": 595.5038, |
|
"eval_samples_per_second": 25.338, |
|
"eval_steps_per_second": 3.169, |
|
"eval_wer": 1.0264442859494156, |
|
"step": 45600 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"eval_loss": 0.16504013538360596, |
|
"eval_runtime": 651.568, |
|
"eval_samples_per_second": 23.158, |
|
"eval_steps_per_second": 2.896, |
|
"eval_wer": 1.0315466066823942, |
|
"step": 45700 |
|
}, |
|
{ |
|
"epoch": 8.29, |
|
"eval_loss": 0.16236093640327454, |
|
"eval_runtime": 656.1816, |
|
"eval_samples_per_second": 22.995, |
|
"eval_steps_per_second": 2.876, |
|
"eval_wer": 1.039008064958578, |
|
"step": 45800 |
|
}, |
|
{ |
|
"epoch": 8.3, |
|
"eval_loss": 0.16241197288036346, |
|
"eval_runtime": 630.0031, |
|
"eval_samples_per_second": 23.951, |
|
"eval_steps_per_second": 2.995, |
|
"eval_wer": 1.0350334973147284, |
|
"step": 45900 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 0.0001344467362290706, |
|
"loss": 0.0884, |
|
"step": 46000 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"eval_loss": 0.1615293174982071, |
|
"eval_runtime": 586.0849, |
|
"eval_samples_per_second": 25.745, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.03177215730022, |
|
"step": 46000 |
|
}, |
|
{ |
|
"epoch": 8.34, |
|
"eval_loss": 0.16276471316814423, |
|
"eval_runtime": 757.1338, |
|
"eval_samples_per_second": 19.929, |
|
"eval_steps_per_second": 2.492, |
|
"eval_wer": 1.0410136366684346, |
|
"step": 46100 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"eval_loss": 0.16269972920417786, |
|
"eval_runtime": 823.1858, |
|
"eval_samples_per_second": 18.33, |
|
"eval_steps_per_second": 2.292, |
|
"eval_wer": 1.0429460568265638, |
|
"step": 46200 |
|
}, |
|
{ |
|
"epoch": 8.38, |
|
"eval_loss": 0.1644161343574524, |
|
"eval_runtime": 582.4378, |
|
"eval_samples_per_second": 25.907, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0320159958059778, |
|
"step": 46300 |
|
}, |
|
{ |
|
"epoch": 8.39, |
|
"eval_loss": 0.16325706243515015, |
|
"eval_runtime": 583.1236, |
|
"eval_samples_per_second": 25.876, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.017660003779497, |
|
"step": 46400 |
|
}, |
|
{ |
|
"epoch": 8.41, |
|
"learning_rate": 0.0001326267896141713, |
|
"loss": 0.0893, |
|
"step": 46500 |
|
}, |
|
{ |
|
"epoch": 8.41, |
|
"eval_loss": 0.1654362827539444, |
|
"eval_runtime": 833.0769, |
|
"eval_samples_per_second": 18.112, |
|
"eval_steps_per_second": 2.265, |
|
"eval_wer": 1.0189279640094366, |
|
"step": 46500 |
|
}, |
|
{ |
|
"epoch": 8.43, |
|
"eval_loss": 0.1598113626241684, |
|
"eval_runtime": 789.1667, |
|
"eval_samples_per_second": 19.12, |
|
"eval_steps_per_second": 2.391, |
|
"eval_wer": 1.0154044976012386, |
|
"step": 46600 |
|
}, |
|
{ |
|
"epoch": 8.45, |
|
"eval_loss": 0.16180771589279175, |
|
"eval_runtime": 594.7754, |
|
"eval_samples_per_second": 25.369, |
|
"eval_steps_per_second": 3.173, |
|
"eval_wer": 1.024962967026938, |
|
"step": 46700 |
|
}, |
|
{ |
|
"epoch": 8.47, |
|
"eval_loss": 0.16394685208797455, |
|
"eval_runtime": 602.2498, |
|
"eval_samples_per_second": 25.054, |
|
"eval_steps_per_second": 3.133, |
|
"eval_wer": 1.0402150655620783, |
|
"step": 46800 |
|
}, |
|
{ |
|
"epoch": 8.48, |
|
"eval_loss": 0.16158275306224823, |
|
"eval_runtime": 670.3939, |
|
"eval_samples_per_second": 22.508, |
|
"eval_steps_per_second": 2.815, |
|
"eval_wer": 1.0336009460934024, |
|
"step": 46900 |
|
}, |
|
{ |
|
"epoch": 8.5, |
|
"learning_rate": 0.00013080684299927203, |
|
"loss": 0.0869, |
|
"step": 47000 |
|
}, |
|
{ |
|
"epoch": 8.5, |
|
"eval_loss": 0.16125723719596863, |
|
"eval_runtime": 671.1005, |
|
"eval_samples_per_second": 22.484, |
|
"eval_steps_per_second": 2.812, |
|
"eval_wer": 1.029620282486909, |
|
"step": 47000 |
|
}, |
|
{ |
|
"epoch": 8.52, |
|
"eval_loss": 0.16476690769195557, |
|
"eval_runtime": 593.5391, |
|
"eval_samples_per_second": 25.422, |
|
"eval_steps_per_second": 3.179, |
|
"eval_wer": 1.056759508177734, |
|
"step": 47100 |
|
}, |
|
{ |
|
"epoch": 8.54, |
|
"eval_loss": 0.1624673455953598, |
|
"eval_runtime": 581.8717, |
|
"eval_samples_per_second": 25.932, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0255786592539762, |
|
"step": 47200 |
|
}, |
|
{ |
|
"epoch": 8.56, |
|
"eval_loss": 0.1608557254076004, |
|
"eval_runtime": 761.7175, |
|
"eval_samples_per_second": 19.809, |
|
"eval_steps_per_second": 2.477, |
|
"eval_wer": 1.0390202568838658, |
|
"step": 47300 |
|
}, |
|
{ |
|
"epoch": 8.57, |
|
"eval_loss": 0.16064698994159698, |
|
"eval_runtime": 722.0512, |
|
"eval_samples_per_second": 20.897, |
|
"eval_steps_per_second": 2.613, |
|
"eval_wer": 1.0449516285364204, |
|
"step": 47400 |
|
}, |
|
{ |
|
"epoch": 8.59, |
|
"learning_rate": 0.0001289905362776025, |
|
"loss": 0.0894, |
|
"step": 47500 |
|
}, |
|
{ |
|
"epoch": 8.59, |
|
"eval_loss": 0.16054730117321014, |
|
"eval_runtime": 580.1173, |
|
"eval_samples_per_second": 26.01, |
|
"eval_steps_per_second": 3.253, |
|
"eval_wer": 1.0445492950019202, |
|
"step": 47500 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"eval_loss": 0.1660243272781372, |
|
"eval_runtime": 580.8578, |
|
"eval_samples_per_second": 25.977, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.0402150655620783, |
|
"step": 47600 |
|
}, |
|
{ |
|
"epoch": 8.63, |
|
"eval_loss": 0.16181260347366333, |
|
"eval_runtime": 815.8627, |
|
"eval_samples_per_second": 18.495, |
|
"eval_steps_per_second": 2.313, |
|
"eval_wer": 1.044366416122602, |
|
"step": 47700 |
|
}, |
|
{ |
|
"epoch": 8.65, |
|
"eval_loss": 0.16689060628414154, |
|
"eval_runtime": 695.8821, |
|
"eval_samples_per_second": 21.683, |
|
"eval_steps_per_second": 2.712, |
|
"eval_wer": 1.033320531811781, |
|
"step": 47800 |
|
}, |
|
{ |
|
"epoch": 8.66, |
|
"eval_loss": 0.16267940402030945, |
|
"eval_runtime": 581.4066, |
|
"eval_samples_per_second": 25.953, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0363624171711077, |
|
"step": 47900 |
|
}, |
|
{ |
|
"epoch": 8.68, |
|
"learning_rate": 0.00012717058966270323, |
|
"loss": 0.0885, |
|
"step": 48000 |
|
}, |
|
{ |
|
"epoch": 8.68, |
|
"eval_loss": 0.1616200953722, |
|
"eval_runtime": 580.4014, |
|
"eval_samples_per_second": 25.998, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0333510116250009, |
|
"step": 48000 |
|
}, |
|
{ |
|
"epoch": 8.7, |
|
"eval_loss": 0.16262862086296082, |
|
"eval_runtime": 591.4018, |
|
"eval_samples_per_second": 25.514, |
|
"eval_steps_per_second": 3.191, |
|
"eval_wer": 1.0563632706058776, |
|
"step": 48100 |
|
}, |
|
{ |
|
"epoch": 8.72, |
|
"eval_loss": 0.16235637664794922, |
|
"eval_runtime": 582.9904, |
|
"eval_samples_per_second": 25.882, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0396054692976842, |
|
"step": 48200 |
|
}, |
|
{ |
|
"epoch": 8.74, |
|
"eval_loss": 0.1622648388147354, |
|
"eval_runtime": 580.0532, |
|
"eval_samples_per_second": 26.013, |
|
"eval_steps_per_second": 3.253, |
|
"eval_wer": 1.0395871814097524, |
|
"step": 48300 |
|
}, |
|
{ |
|
"epoch": 8.76, |
|
"eval_loss": 0.16115820407867432, |
|
"eval_runtime": 593.5347, |
|
"eval_samples_per_second": 25.422, |
|
"eval_steps_per_second": 3.179, |
|
"eval_wer": 1.0111860914516315, |
|
"step": 48400 |
|
}, |
|
{ |
|
"epoch": 8.77, |
|
"learning_rate": 0.00012535064304780393, |
|
"loss": 0.0888, |
|
"step": 48500 |
|
}, |
|
{ |
|
"epoch": 8.77, |
|
"eval_loss": 0.16379259526729584, |
|
"eval_runtime": 598.4046, |
|
"eval_samples_per_second": 25.215, |
|
"eval_steps_per_second": 3.153, |
|
"eval_wer": 1.029211852989765, |
|
"step": 48500 |
|
}, |
|
{ |
|
"epoch": 8.79, |
|
"eval_loss": 0.16386225819587708, |
|
"eval_runtime": 707.2069, |
|
"eval_samples_per_second": 21.336, |
|
"eval_steps_per_second": 2.668, |
|
"eval_wer": 0.9988173832470755, |
|
"step": 48600 |
|
}, |
|
{ |
|
"epoch": 8.81, |
|
"eval_loss": 0.1618259996175766, |
|
"eval_runtime": 581.5329, |
|
"eval_samples_per_second": 25.947, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0127161780752607, |
|
"step": 48700 |
|
}, |
|
{ |
|
"epoch": 8.83, |
|
"eval_loss": 0.1584457904100418, |
|
"eval_runtime": 592.4893, |
|
"eval_samples_per_second": 25.467, |
|
"eval_steps_per_second": 3.185, |
|
"eval_wer": 1.004230598074895, |
|
"step": 48800 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"eval_loss": 0.16147887706756592, |
|
"eval_runtime": 892.6436, |
|
"eval_samples_per_second": 16.904, |
|
"eval_steps_per_second": 2.114, |
|
"eval_wer": 1.0040903909340844, |
|
"step": 48900 |
|
}, |
|
{ |
|
"epoch": 8.86, |
|
"learning_rate": 0.00012353069643290462, |
|
"loss": 0.0887, |
|
"step": 49000 |
|
}, |
|
{ |
|
"epoch": 8.86, |
|
"eval_loss": 0.16373465955257416, |
|
"eval_runtime": 597.5877, |
|
"eval_samples_per_second": 25.25, |
|
"eval_steps_per_second": 3.158, |
|
"eval_wer": 1.0268770992971354, |
|
"step": 49000 |
|
}, |
|
{ |
|
"epoch": 8.88, |
|
"eval_loss": 0.16268499195575714, |
|
"eval_runtime": 582.3813, |
|
"eval_samples_per_second": 25.909, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 0.9988783428735148, |
|
"step": 49100 |
|
}, |
|
{ |
|
"epoch": 8.9, |
|
"eval_loss": 0.1583053022623062, |
|
"eval_runtime": 597.6851, |
|
"eval_samples_per_second": 25.246, |
|
"eval_steps_per_second": 3.157, |
|
"eval_wer": 1.0103631364946997, |
|
"step": 49200 |
|
}, |
|
{ |
|
"epoch": 8.92, |
|
"eval_loss": 0.1600298136472702, |
|
"eval_runtime": 661.9601, |
|
"eval_samples_per_second": 22.794, |
|
"eval_steps_per_second": 2.851, |
|
"eval_wer": 1.021360253104369, |
|
"step": 49300 |
|
}, |
|
{ |
|
"epoch": 8.94, |
|
"eval_loss": 0.15990710258483887, |
|
"eval_runtime": 728.4467, |
|
"eval_samples_per_second": 20.714, |
|
"eval_steps_per_second": 2.59, |
|
"eval_wer": 1.0126247386356015, |
|
"step": 49400 |
|
}, |
|
{ |
|
"epoch": 8.95, |
|
"learning_rate": 0.00012171074981800533, |
|
"loss": 0.0893, |
|
"step": 49500 |
|
}, |
|
{ |
|
"epoch": 8.95, |
|
"eval_loss": 0.15952347218990326, |
|
"eval_runtime": 582.1344, |
|
"eval_samples_per_second": 25.92, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0515779399303842, |
|
"step": 49500 |
|
}, |
|
{ |
|
"epoch": 8.97, |
|
"eval_loss": 0.16249197721481323, |
|
"eval_runtime": 582.3785, |
|
"eval_samples_per_second": 25.909, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0463536999445266, |
|
"step": 49600 |
|
}, |
|
{ |
|
"epoch": 8.99, |
|
"eval_loss": 0.15948396921157837, |
|
"eval_runtime": 788.7938, |
|
"eval_samples_per_second": 19.129, |
|
"eval_steps_per_second": 2.392, |
|
"eval_wer": 1.0360941948147742, |
|
"step": 49700 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"eval_loss": 0.16136983036994934, |
|
"eval_runtime": 672.0772, |
|
"eval_samples_per_second": 22.451, |
|
"eval_steps_per_second": 2.808, |
|
"eval_wer": 1.0468962406198374, |
|
"step": 49800 |
|
}, |
|
{ |
|
"epoch": 9.03, |
|
"eval_loss": 0.16116857528686523, |
|
"eval_runtime": 580.6233, |
|
"eval_samples_per_second": 25.988, |
|
"eval_steps_per_second": 3.25, |
|
"eval_wer": 1.0303944697426894, |
|
"step": 49900 |
|
}, |
|
{ |
|
"epoch": 9.04, |
|
"learning_rate": 0.00011989080320310603, |
|
"loss": 0.0834, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 9.04, |
|
"eval_loss": 0.16431789100170135, |
|
"eval_runtime": 582.7513, |
|
"eval_samples_per_second": 25.893, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.033533890504319, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"eval_loss": 0.16401399672031403, |
|
"eval_runtime": 885.9925, |
|
"eval_samples_per_second": 17.031, |
|
"eval_steps_per_second": 2.13, |
|
"eval_wer": 1.017531988563974, |
|
"step": 50100 |
|
}, |
|
{ |
|
"epoch": 9.08, |
|
"eval_loss": 0.16546601057052612, |
|
"eval_runtime": 648.7007, |
|
"eval_samples_per_second": 23.26, |
|
"eval_steps_per_second": 2.909, |
|
"eval_wer": 1.0263833263229762, |
|
"step": 50200 |
|
}, |
|
{ |
|
"epoch": 9.1, |
|
"eval_loss": 0.16776497662067413, |
|
"eval_runtime": 581.0662, |
|
"eval_samples_per_second": 25.968, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0243046030613925, |
|
"step": 50300 |
|
}, |
|
{ |
|
"epoch": 9.12, |
|
"eval_loss": 0.16594190895557404, |
|
"eval_runtime": 585.0092, |
|
"eval_samples_per_second": 25.793, |
|
"eval_steps_per_second": 3.226, |
|
"eval_wer": 1.0145205830178672, |
|
"step": 50400 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"learning_rate": 0.00011807085658820674, |
|
"loss": 0.079, |
|
"step": 50500 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"eval_loss": 0.16435874998569489, |
|
"eval_runtime": 814.5284, |
|
"eval_samples_per_second": 18.525, |
|
"eval_steps_per_second": 2.317, |
|
"eval_wer": 1.0315587986076822, |
|
"step": 50500 |
|
}, |
|
{ |
|
"epoch": 9.15, |
|
"eval_loss": 0.1629723608493805, |
|
"eval_runtime": 758.0979, |
|
"eval_samples_per_second": 19.904, |
|
"eval_steps_per_second": 2.489, |
|
"eval_wer": 1.0326377839956598, |
|
"step": 50600 |
|
}, |
|
{ |
|
"epoch": 9.17, |
|
"eval_loss": 0.16343791782855988, |
|
"eval_runtime": 581.3896, |
|
"eval_samples_per_second": 25.953, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.015367921825375, |
|
"step": 50700 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"eval_loss": 0.169687420129776, |
|
"eval_runtime": 582.3186, |
|
"eval_samples_per_second": 25.912, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.009491413836616, |
|
"step": 50800 |
|
}, |
|
{ |
|
"epoch": 9.21, |
|
"eval_loss": 0.1677592247724533, |
|
"eval_runtime": 702.7189, |
|
"eval_samples_per_second": 21.472, |
|
"eval_steps_per_second": 2.685, |
|
"eval_wer": 1.0050291691812512, |
|
"step": 50900 |
|
}, |
|
{ |
|
"epoch": 9.23, |
|
"learning_rate": 0.00011625090997330743, |
|
"loss": 0.078, |
|
"step": 51000 |
|
}, |
|
{ |
|
"epoch": 9.23, |
|
"eval_loss": 0.16258232295513153, |
|
"eval_runtime": 585.8429, |
|
"eval_samples_per_second": 25.756, |
|
"eval_steps_per_second": 3.221, |
|
"eval_wer": 1.0159409423139054, |
|
"step": 51000 |
|
}, |
|
{ |
|
"epoch": 9.24, |
|
"eval_loss": 0.1665642261505127, |
|
"eval_runtime": 584.7636, |
|
"eval_samples_per_second": 25.804, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.0237559664234377, |
|
"step": 51100 |
|
}, |
|
{ |
|
"epoch": 9.26, |
|
"eval_loss": 0.1644172966480255, |
|
"eval_runtime": 581.2024, |
|
"eval_samples_per_second": 25.962, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0244082344263394, |
|
"step": 51200 |
|
}, |
|
{ |
|
"epoch": 9.28, |
|
"eval_loss": 0.16548845171928406, |
|
"eval_runtime": 773.778, |
|
"eval_samples_per_second": 19.5, |
|
"eval_steps_per_second": 2.439, |
|
"eval_wer": 1.0345092445273496, |
|
"step": 51300 |
|
}, |
|
{ |
|
"epoch": 9.3, |
|
"eval_loss": 0.16148586571216583, |
|
"eval_runtime": 753.2674, |
|
"eval_samples_per_second": 20.031, |
|
"eval_steps_per_second": 2.505, |
|
"eval_wer": 1.0236767189090665, |
|
"step": 51400 |
|
}, |
|
{ |
|
"epoch": 9.32, |
|
"learning_rate": 0.00011443460325163794, |
|
"loss": 0.0776, |
|
"step": 51500 |
|
}, |
|
{ |
|
"epoch": 9.32, |
|
"eval_loss": 0.1664086878299713, |
|
"eval_runtime": 600.4636, |
|
"eval_samples_per_second": 25.129, |
|
"eval_steps_per_second": 3.143, |
|
"eval_wer": 1.0179952817249136, |
|
"step": 51500 |
|
}, |
|
{ |
|
"epoch": 9.33, |
|
"eval_loss": 0.16034889221191406, |
|
"eval_runtime": 598.9514, |
|
"eval_samples_per_second": 25.192, |
|
"eval_steps_per_second": 3.151, |
|
"eval_wer": 1.0207933285784825, |
|
"step": 51600 |
|
}, |
|
{ |
|
"epoch": 9.35, |
|
"eval_loss": 0.1594148576259613, |
|
"eval_runtime": 1099.0175, |
|
"eval_samples_per_second": 13.73, |
|
"eval_steps_per_second": 1.717, |
|
"eval_wer": 1.0229695872423694, |
|
"step": 51700 |
|
}, |
|
{ |
|
"epoch": 9.37, |
|
"eval_loss": 0.16220493614673615, |
|
"eval_runtime": 635.6696, |
|
"eval_samples_per_second": 23.737, |
|
"eval_steps_per_second": 2.969, |
|
"eval_wer": 1.0201410605755807, |
|
"step": 51800 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"eval_loss": 0.15961703658103943, |
|
"eval_runtime": 580.4546, |
|
"eval_samples_per_second": 25.995, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.003907512054766, |
|
"step": 51900 |
|
}, |
|
{ |
|
"epoch": 9.41, |
|
"learning_rate": 0.00011261465663673865, |
|
"loss": 0.0782, |
|
"step": 52000 |
|
}, |
|
{ |
|
"epoch": 9.41, |
|
"eval_loss": 0.1644771248102188, |
|
"eval_runtime": 580.2702, |
|
"eval_samples_per_second": 26.003, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0203605152307627, |
|
"step": 52000 |
|
}, |
|
{ |
|
"epoch": 9.42, |
|
"eval_loss": 0.16403250396251678, |
|
"eval_runtime": 586.7485, |
|
"eval_samples_per_second": 25.716, |
|
"eval_steps_per_second": 3.216, |
|
"eval_wer": 1.0318209250013717, |
|
"step": 52100 |
|
}, |
|
{ |
|
"epoch": 9.44, |
|
"eval_loss": 0.16205865144729614, |
|
"eval_runtime": 580.5387, |
|
"eval_samples_per_second": 25.991, |
|
"eval_steps_per_second": 3.25, |
|
"eval_wer": 1.0290167821851588, |
|
"step": 52200 |
|
}, |
|
{ |
|
"epoch": 9.46, |
|
"eval_loss": 0.16380777955055237, |
|
"eval_runtime": 594.1221, |
|
"eval_samples_per_second": 25.397, |
|
"eval_steps_per_second": 3.176, |
|
"eval_wer": 1.031766061337576, |
|
"step": 52300 |
|
}, |
|
{ |
|
"epoch": 9.48, |
|
"eval_loss": 0.16133266687393188, |
|
"eval_runtime": 585.3086, |
|
"eval_samples_per_second": 25.78, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0216528593112781, |
|
"step": 52400 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"learning_rate": 0.00011079471002183935, |
|
"loss": 0.0782, |
|
"step": 52500 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"eval_loss": 0.16088727116584778, |
|
"eval_runtime": 626.7548, |
|
"eval_samples_per_second": 24.075, |
|
"eval_steps_per_second": 3.011, |
|
"eval_wer": 1.0260541443402036, |
|
"step": 52500 |
|
}, |
|
{ |
|
"epoch": 9.52, |
|
"eval_loss": 0.16250905394554138, |
|
"eval_runtime": 792.3097, |
|
"eval_samples_per_second": 19.044, |
|
"eval_steps_per_second": 2.382, |
|
"eval_wer": 1.010113202026298, |
|
"step": 52600 |
|
}, |
|
{ |
|
"epoch": 9.53, |
|
"eval_loss": 0.1612967550754547, |
|
"eval_runtime": 579.6946, |
|
"eval_samples_per_second": 26.029, |
|
"eval_steps_per_second": 3.255, |
|
"eval_wer": 1.0057545887358803, |
|
"step": 52700 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"eval_loss": 0.15985870361328125, |
|
"eval_runtime": 581.2133, |
|
"eval_samples_per_second": 25.961, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.006803094310638, |
|
"step": 52800 |
|
}, |
|
{ |
|
"epoch": 9.57, |
|
"eval_loss": 0.159987673163414, |
|
"eval_runtime": 593.2496, |
|
"eval_samples_per_second": 25.434, |
|
"eval_steps_per_second": 3.181, |
|
"eval_wer": 1.011033692385533, |
|
"step": 52900 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 0.00010897476340694006, |
|
"loss": 0.0797, |
|
"step": 53000 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"eval_loss": 0.15943679213523865, |
|
"eval_runtime": 669.0711, |
|
"eval_samples_per_second": 22.552, |
|
"eval_steps_per_second": 2.82, |
|
"eval_wer": 1.0170625994403906, |
|
"step": 53000 |
|
}, |
|
{ |
|
"epoch": 9.61, |
|
"eval_loss": 0.1583079844713211, |
|
"eval_runtime": 605.5808, |
|
"eval_samples_per_second": 24.917, |
|
"eval_steps_per_second": 3.116, |
|
"eval_wer": 1.012368708204556, |
|
"step": 53100 |
|
}, |
|
{ |
|
"epoch": 9.62, |
|
"eval_loss": 0.16463600099086761, |
|
"eval_runtime": 612.4932, |
|
"eval_samples_per_second": 24.635, |
|
"eval_steps_per_second": 3.081, |
|
"eval_wer": 1.0093329188078735, |
|
"step": 53200 |
|
}, |
|
{ |
|
"epoch": 9.64, |
|
"eval_loss": 0.15795104205608368, |
|
"eval_runtime": 780.4208, |
|
"eval_samples_per_second": 19.334, |
|
"eval_steps_per_second": 2.418, |
|
"eval_wer": 1.0200922928744294, |
|
"step": 53300 |
|
}, |
|
{ |
|
"epoch": 9.66, |
|
"eval_loss": 0.15989932417869568, |
|
"eval_runtime": 794.8985, |
|
"eval_samples_per_second": 18.982, |
|
"eval_steps_per_second": 2.374, |
|
"eval_wer": 1.0206775052882475, |
|
"step": 53400 |
|
}, |
|
{ |
|
"epoch": 9.68, |
|
"learning_rate": 0.00010715481679204077, |
|
"loss": 0.0783, |
|
"step": 53500 |
|
}, |
|
{ |
|
"epoch": 9.68, |
|
"eval_loss": 0.15769976377487183, |
|
"eval_runtime": 591.2607, |
|
"eval_samples_per_second": 25.52, |
|
"eval_steps_per_second": 3.191, |
|
"eval_wer": 1.0226404052595965, |
|
"step": 53500 |
|
}, |
|
{ |
|
"epoch": 9.7, |
|
"eval_loss": 0.15931198000907898, |
|
"eval_runtime": 580.3684, |
|
"eval_samples_per_second": 25.999, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0160262857909206, |
|
"step": 53600 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"eval_loss": 0.15701308846473694, |
|
"eval_runtime": 631.6476, |
|
"eval_samples_per_second": 23.888, |
|
"eval_steps_per_second": 2.987, |
|
"eval_wer": 1.01732472583408, |
|
"step": 53700 |
|
}, |
|
{ |
|
"epoch": 9.73, |
|
"eval_loss": 0.16138727962970734, |
|
"eval_runtime": 823.2091, |
|
"eval_samples_per_second": 18.329, |
|
"eval_steps_per_second": 2.292, |
|
"eval_wer": 1.0299372725443938, |
|
"step": 53800 |
|
}, |
|
{ |
|
"epoch": 9.75, |
|
"eval_loss": 0.16104823350906372, |
|
"eval_runtime": 592.3865, |
|
"eval_samples_per_second": 25.472, |
|
"eval_steps_per_second": 3.185, |
|
"eval_wer": 1.0184098071847016, |
|
"step": 53900 |
|
}, |
|
{ |
|
"epoch": 9.77, |
|
"learning_rate": 0.00010533487017714146, |
|
"loss": 0.0779, |
|
"step": 54000 |
|
}, |
|
{ |
|
"epoch": 9.77, |
|
"eval_loss": 0.16055870056152344, |
|
"eval_runtime": 578.7328, |
|
"eval_samples_per_second": 26.072, |
|
"eval_steps_per_second": 3.261, |
|
"eval_wer": 1.0173003419835043, |
|
"step": 54000 |
|
}, |
|
{ |
|
"epoch": 9.79, |
|
"eval_loss": 0.15772290527820587, |
|
"eval_runtime": 762.4369, |
|
"eval_samples_per_second": 19.79, |
|
"eval_steps_per_second": 2.475, |
|
"eval_wer": 1.0031699005748493, |
|
"step": 54100 |
|
}, |
|
{ |
|
"epoch": 9.8, |
|
"eval_loss": 0.1589614897966385, |
|
"eval_runtime": 769.937, |
|
"eval_samples_per_second": 19.598, |
|
"eval_steps_per_second": 2.451, |
|
"eval_wer": 1.007016453003176, |
|
"step": 54200 |
|
}, |
|
{ |
|
"epoch": 9.82, |
|
"eval_loss": 0.15804855525493622, |
|
"eval_runtime": 581.4557, |
|
"eval_samples_per_second": 25.95, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0256883865815671, |
|
"step": 54300 |
|
}, |
|
{ |
|
"epoch": 9.84, |
|
"eval_loss": 0.15920314192771912, |
|
"eval_runtime": 579.5344, |
|
"eval_samples_per_second": 26.036, |
|
"eval_steps_per_second": 3.256, |
|
"eval_wer": 1.0107837579171315, |
|
"step": 54400 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 0.00010351856345547196, |
|
"loss": 0.0778, |
|
"step": 54500 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"eval_loss": 0.1616947501897812, |
|
"eval_runtime": 784.3278, |
|
"eval_samples_per_second": 19.238, |
|
"eval_steps_per_second": 2.406, |
|
"eval_wer": 0.9907463287064977, |
|
"step": 54500 |
|
}, |
|
{ |
|
"epoch": 9.88, |
|
"eval_loss": 0.16045895218849182, |
|
"eval_runtime": 696.7226, |
|
"eval_samples_per_second": 21.657, |
|
"eval_steps_per_second": 2.708, |
|
"eval_wer": 1.0188548124577093, |
|
"step": 54600 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"eval_loss": 0.16049787402153015, |
|
"eval_runtime": 585.856, |
|
"eval_samples_per_second": 25.755, |
|
"eval_steps_per_second": 3.221, |
|
"eval_wer": 1.0176843876300725, |
|
"step": 54700 |
|
}, |
|
{ |
|
"epoch": 9.91, |
|
"eval_loss": 0.15361995995044708, |
|
"eval_runtime": 592.9048, |
|
"eval_samples_per_second": 25.449, |
|
"eval_steps_per_second": 3.183, |
|
"eval_wer": 1.0274927915241736, |
|
"step": 54800 |
|
}, |
|
{ |
|
"epoch": 9.93, |
|
"eval_loss": 0.16578349471092224, |
|
"eval_runtime": 796.0097, |
|
"eval_samples_per_second": 18.956, |
|
"eval_steps_per_second": 2.371, |
|
"eval_wer": 1.028169443377651, |
|
"step": 54900 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"learning_rate": 0.00010169861684057267, |
|
"loss": 0.0777, |
|
"step": 55000 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"eval_loss": 0.15434084832668304, |
|
"eval_runtime": 657.9027, |
|
"eval_samples_per_second": 22.935, |
|
"eval_steps_per_second": 2.868, |
|
"eval_wer": 1.038489908133843, |
|
"step": 55000 |
|
}, |
|
{ |
|
"epoch": 9.97, |
|
"eval_loss": 0.15585801005363464, |
|
"eval_runtime": 593.5105, |
|
"eval_samples_per_second": 25.423, |
|
"eval_steps_per_second": 3.179, |
|
"eval_wer": 1.0375328419987442, |
|
"step": 55100 |
|
}, |
|
{ |
|
"epoch": 9.99, |
|
"eval_loss": 0.1590491086244583, |
|
"eval_runtime": 599.7954, |
|
"eval_samples_per_second": 25.157, |
|
"eval_steps_per_second": 3.146, |
|
"eval_wer": 1.0215431319836872, |
|
"step": 55200 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 0.16239939630031586, |
|
"eval_runtime": 676.8287, |
|
"eval_samples_per_second": 22.294, |
|
"eval_steps_per_second": 2.788, |
|
"eval_wer": 1.0241765878458697, |
|
"step": 55300 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"eval_loss": 0.16353543102741241, |
|
"eval_runtime": 778.4878, |
|
"eval_samples_per_second": 19.382, |
|
"eval_steps_per_second": 2.424, |
|
"eval_wer": 1.024353370762544, |
|
"step": 55400 |
|
}, |
|
{ |
|
"epoch": 10.04, |
|
"learning_rate": 9.987867022567338e-05, |
|
"loss": 0.0712, |
|
"step": 55500 |
|
}, |
|
{ |
|
"epoch": 10.04, |
|
"eval_loss": 0.1628965139389038, |
|
"eval_runtime": 581.6719, |
|
"eval_samples_per_second": 25.941, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.029803161366227, |
|
"step": 55500 |
|
}, |
|
{ |
|
"epoch": 10.06, |
|
"eval_loss": 0.16010913252830505, |
|
"eval_runtime": 580.2062, |
|
"eval_samples_per_second": 26.006, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0298824088805985, |
|
"step": 55600 |
|
}, |
|
{ |
|
"epoch": 10.08, |
|
"eval_loss": 0.16253387928009033, |
|
"eval_runtime": 810.8172, |
|
"eval_samples_per_second": 18.61, |
|
"eval_steps_per_second": 2.327, |
|
"eval_wer": 1.011667672500503, |
|
"step": 55700 |
|
}, |
|
{ |
|
"epoch": 10.09, |
|
"eval_loss": 0.16501325368881226, |
|
"eval_runtime": 598.9657, |
|
"eval_samples_per_second": 25.192, |
|
"eval_steps_per_second": 3.15, |
|
"eval_wer": 1.0232804813372103, |
|
"step": 55800 |
|
}, |
|
{ |
|
"epoch": 10.11, |
|
"eval_loss": 0.16311536729335785, |
|
"eval_runtime": 580.9085, |
|
"eval_samples_per_second": 25.975, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0061020586065847, |
|
"step": 55900 |
|
}, |
|
{ |
|
"epoch": 10.13, |
|
"learning_rate": 9.805872361077407e-05, |
|
"loss": 0.0667, |
|
"step": 56000 |
|
}, |
|
{ |
|
"epoch": 10.13, |
|
"eval_loss": 0.1636841744184494, |
|
"eval_runtime": 600.3431, |
|
"eval_samples_per_second": 25.134, |
|
"eval_steps_per_second": 3.143, |
|
"eval_wer": 1.0226343092969525, |
|
"step": 56000 |
|
}, |
|
{ |
|
"epoch": 10.15, |
|
"eval_loss": 0.1607149839401245, |
|
"eval_runtime": 1230.1922, |
|
"eval_samples_per_second": 12.266, |
|
"eval_steps_per_second": 1.534, |
|
"eval_wer": 1.004212310186963, |
|
"step": 56100 |
|
}, |
|
{ |
|
"epoch": 10.17, |
|
"eval_loss": 0.1599477082490921, |
|
"eval_runtime": 596.4073, |
|
"eval_samples_per_second": 25.3, |
|
"eval_steps_per_second": 3.164, |
|
"eval_wer": 1.0117225361642983, |
|
"step": 56200 |
|
}, |
|
{ |
|
"epoch": 10.18, |
|
"eval_loss": 0.16232724487781525, |
|
"eval_runtime": 580.397, |
|
"eval_samples_per_second": 25.998, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0245972092683016, |
|
"step": 56300 |
|
}, |
|
{ |
|
"epoch": 10.2, |
|
"eval_loss": 0.16392558813095093, |
|
"eval_runtime": 580.3269, |
|
"eval_samples_per_second": 26.001, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 1.0294252116823028, |
|
"step": 56400 |
|
}, |
|
{ |
|
"epoch": 10.22, |
|
"learning_rate": 9.624241688910458e-05, |
|
"loss": 0.0695, |
|
"step": 56500 |
|
}, |
|
{ |
|
"epoch": 10.22, |
|
"eval_loss": 0.16502028703689575, |
|
"eval_runtime": 859.9983, |
|
"eval_samples_per_second": 17.545, |
|
"eval_steps_per_second": 2.194, |
|
"eval_wer": 1.0231890418975513, |
|
"step": 56500 |
|
}, |
|
{ |
|
"epoch": 10.24, |
|
"eval_loss": 0.162032812833786, |
|
"eval_runtime": 629.7937, |
|
"eval_samples_per_second": 23.959, |
|
"eval_steps_per_second": 2.996, |
|
"eval_wer": 1.02889486293228, |
|
"step": 56600 |
|
}, |
|
{ |
|
"epoch": 10.26, |
|
"eval_loss": 0.16672161221504211, |
|
"eval_runtime": 591.7678, |
|
"eval_samples_per_second": 25.498, |
|
"eval_steps_per_second": 3.189, |
|
"eval_wer": 1.0208664801302099, |
|
"step": 56700 |
|
}, |
|
{ |
|
"epoch": 10.27, |
|
"eval_loss": 0.15804210305213928, |
|
"eval_runtime": 580.1264, |
|
"eval_samples_per_second": 26.01, |
|
"eval_steps_per_second": 3.253, |
|
"eval_wer": 1.0163493718110495, |
|
"step": 56800 |
|
}, |
|
{ |
|
"epoch": 10.29, |
|
"eval_loss": 0.16456495225429535, |
|
"eval_runtime": 784.7617, |
|
"eval_samples_per_second": 19.227, |
|
"eval_steps_per_second": 2.405, |
|
"eval_wer": 1.0293459641679317, |
|
"step": 56900 |
|
}, |
|
{ |
|
"epoch": 10.31, |
|
"learning_rate": 9.442247027420528e-05, |
|
"loss": 0.0686, |
|
"step": 57000 |
|
}, |
|
{ |
|
"epoch": 10.31, |
|
"eval_loss": 0.16356460750102997, |
|
"eval_runtime": 816.4454, |
|
"eval_samples_per_second": 18.481, |
|
"eval_steps_per_second": 2.311, |
|
"eval_wer": 1.0105764951872376, |
|
"step": 57000 |
|
}, |
|
{ |
|
"epoch": 10.33, |
|
"eval_loss": 0.1585777848958969, |
|
"eval_runtime": 581.6554, |
|
"eval_samples_per_second": 25.941, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0043829971409934, |
|
"step": 57100 |
|
}, |
|
{ |
|
"epoch": 10.35, |
|
"eval_loss": 0.15822261571884155, |
|
"eval_runtime": 586.4769, |
|
"eval_samples_per_second": 25.728, |
|
"eval_steps_per_second": 3.218, |
|
"eval_wer": 1.0212810055899977, |
|
"step": 57200 |
|
}, |
|
{ |
|
"epoch": 10.37, |
|
"eval_loss": 0.1626518964767456, |
|
"eval_runtime": 652.945, |
|
"eval_samples_per_second": 23.109, |
|
"eval_steps_per_second": 2.89, |
|
"eval_wer": 1.0151179873569736, |
|
"step": 57300 |
|
}, |
|
{ |
|
"epoch": 10.38, |
|
"eval_loss": 0.1618737131357193, |
|
"eval_runtime": 643.6148, |
|
"eval_samples_per_second": 23.444, |
|
"eval_steps_per_second": 2.932, |
|
"eval_wer": 1.0248044719981957, |
|
"step": 57400 |
|
}, |
|
{ |
|
"epoch": 10.4, |
|
"learning_rate": 9.260252365930599e-05, |
|
"loss": 0.0686, |
|
"step": 57500 |
|
}, |
|
{ |
|
"epoch": 10.4, |
|
"eval_loss": 0.15961088240146637, |
|
"eval_runtime": 581.127, |
|
"eval_samples_per_second": 25.965, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0097535402303055, |
|
"step": 57500 |
|
}, |
|
{ |
|
"epoch": 10.42, |
|
"eval_loss": 0.16058142483234406, |
|
"eval_runtime": 581.0057, |
|
"eval_samples_per_second": 25.97, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0031394207616295, |
|
"step": 57600 |
|
}, |
|
{ |
|
"epoch": 10.44, |
|
"eval_loss": 0.16196614503860474, |
|
"eval_runtime": 661.9802, |
|
"eval_samples_per_second": 22.794, |
|
"eval_steps_per_second": 2.851, |
|
"eval_wer": 1.0045780679455996, |
|
"step": 57700 |
|
}, |
|
{ |
|
"epoch": 10.46, |
|
"eval_loss": 0.15916328132152557, |
|
"eval_runtime": 581.8543, |
|
"eval_samples_per_second": 25.933, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.001773925129387, |
|
"step": 57800 |
|
}, |
|
{ |
|
"epoch": 10.47, |
|
"eval_loss": 0.1592239886522293, |
|
"eval_runtime": 585.3649, |
|
"eval_samples_per_second": 25.777, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0058399322128955, |
|
"step": 57900 |
|
}, |
|
{ |
|
"epoch": 10.49, |
|
"learning_rate": 9.07825770444067e-05, |
|
"loss": 0.0669, |
|
"step": 58000 |
|
}, |
|
{ |
|
"epoch": 10.49, |
|
"eval_loss": 0.16053098440170288, |
|
"eval_runtime": 580.0983, |
|
"eval_samples_per_second": 26.011, |
|
"eval_steps_per_second": 3.253, |
|
"eval_wer": 0.9961168717958097, |
|
"step": 58000 |
|
}, |
|
{ |
|
"epoch": 10.51, |
|
"eval_loss": 0.163193017244339, |
|
"eval_runtime": 597.491, |
|
"eval_samples_per_second": 25.254, |
|
"eval_steps_per_second": 3.158, |
|
"eval_wer": 1.0101924495406691, |
|
"step": 58100 |
|
}, |
|
{ |
|
"epoch": 10.53, |
|
"eval_loss": 0.15927906334400177, |
|
"eval_runtime": 692.2659, |
|
"eval_samples_per_second": 21.797, |
|
"eval_steps_per_second": 2.726, |
|
"eval_wer": 1.0060654828307212, |
|
"step": 58200 |
|
}, |
|
{ |
|
"epoch": 10.55, |
|
"eval_loss": 0.1585976928472519, |
|
"eval_runtime": 598.5348, |
|
"eval_samples_per_second": 25.21, |
|
"eval_steps_per_second": 3.153, |
|
"eval_wer": 1.0091134641526918, |
|
"step": 58300 |
|
}, |
|
{ |
|
"epoch": 10.56, |
|
"eval_loss": 0.1602911651134491, |
|
"eval_runtime": 596.6358, |
|
"eval_samples_per_second": 25.29, |
|
"eval_steps_per_second": 3.163, |
|
"eval_wer": 1.0084916759630096, |
|
"step": 58400 |
|
}, |
|
{ |
|
"epoch": 10.58, |
|
"learning_rate": 8.896263042950739e-05, |
|
"loss": 0.068, |
|
"step": 58500 |
|
}, |
|
{ |
|
"epoch": 10.58, |
|
"eval_loss": 0.15785259008407593, |
|
"eval_runtime": 930.7715, |
|
"eval_samples_per_second": 16.211, |
|
"eval_steps_per_second": 2.027, |
|
"eval_wer": 1.0030784611351902, |
|
"step": 58500 |
|
}, |
|
{ |
|
"epoch": 10.6, |
|
"eval_loss": 0.1590667963027954, |
|
"eval_runtime": 735.2125, |
|
"eval_samples_per_second": 20.523, |
|
"eval_steps_per_second": 2.567, |
|
"eval_wer": 1.0020909151868718, |
|
"step": 58600 |
|
}, |
|
{ |
|
"epoch": 10.62, |
|
"eval_loss": 0.15900607407093048, |
|
"eval_runtime": 583.5509, |
|
"eval_samples_per_second": 25.857, |
|
"eval_steps_per_second": 3.234, |
|
"eval_wer": 1.0162823162219663, |
|
"step": 58700 |
|
}, |
|
{ |
|
"epoch": 10.64, |
|
"eval_loss": 0.15844112634658813, |
|
"eval_runtime": 580.7859, |
|
"eval_samples_per_second": 25.98, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.0044866285059406, |
|
"step": 58800 |
|
}, |
|
{ |
|
"epoch": 10.65, |
|
"eval_loss": 0.1593514233827591, |
|
"eval_runtime": 844.9985, |
|
"eval_samples_per_second": 17.857, |
|
"eval_steps_per_second": 2.233, |
|
"eval_wer": 1.0158129270983827, |
|
"step": 58900 |
|
}, |
|
{ |
|
"epoch": 10.67, |
|
"learning_rate": 8.71426838146081e-05, |
|
"loss": 0.0693, |
|
"step": 59000 |
|
}, |
|
{ |
|
"epoch": 10.67, |
|
"eval_loss": 0.15675154328346252, |
|
"eval_runtime": 736.1944, |
|
"eval_samples_per_second": 20.496, |
|
"eval_steps_per_second": 2.563, |
|
"eval_wer": 1.0052364319111453, |
|
"step": 59000 |
|
}, |
|
{ |
|
"epoch": 10.69, |
|
"eval_loss": 0.15810607373714447, |
|
"eval_runtime": 580.7163, |
|
"eval_samples_per_second": 25.983, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 0.9955011795687716, |
|
"step": 59100 |
|
}, |
|
{ |
|
"epoch": 10.71, |
|
"eval_loss": 0.16217058897018433, |
|
"eval_runtime": 599.9088, |
|
"eval_samples_per_second": 25.152, |
|
"eval_steps_per_second": 3.145, |
|
"eval_wer": 0.9916851069536646, |
|
"step": 59200 |
|
}, |
|
{ |
|
"epoch": 10.73, |
|
"eval_loss": 0.15796062350273132, |
|
"eval_runtime": 618.486, |
|
"eval_samples_per_second": 24.397, |
|
"eval_steps_per_second": 3.051, |
|
"eval_wer": 1.0017861170546747, |
|
"step": 59300 |
|
}, |
|
{ |
|
"epoch": 10.75, |
|
"eval_loss": 0.1600871980190277, |
|
"eval_runtime": 610.0596, |
|
"eval_samples_per_second": 24.734, |
|
"eval_steps_per_second": 3.093, |
|
"eval_wer": 1.0076931048566535, |
|
"step": 59400 |
|
}, |
|
{ |
|
"epoch": 10.76, |
|
"learning_rate": 8.53227371997088e-05, |
|
"loss": 0.0699, |
|
"step": 59500 |
|
}, |
|
{ |
|
"epoch": 10.76, |
|
"eval_loss": 0.16046388447284698, |
|
"eval_runtime": 593.6048, |
|
"eval_samples_per_second": 25.419, |
|
"eval_steps_per_second": 3.179, |
|
"eval_wer": 0.9996708180172272, |
|
"step": 59500 |
|
}, |
|
{ |
|
"epoch": 10.78, |
|
"eval_loss": 0.15849190950393677, |
|
"eval_runtime": 592.6817, |
|
"eval_samples_per_second": 25.459, |
|
"eval_steps_per_second": 3.184, |
|
"eval_wer": 1.0008717226580834, |
|
"step": 59600 |
|
}, |
|
{ |
|
"epoch": 10.8, |
|
"eval_loss": 0.1540997177362442, |
|
"eval_runtime": 789.9508, |
|
"eval_samples_per_second": 19.101, |
|
"eval_steps_per_second": 2.389, |
|
"eval_wer": 1.0058094523996757, |
|
"step": 59700 |
|
}, |
|
{ |
|
"epoch": 10.82, |
|
"eval_loss": 0.15827548503875732, |
|
"eval_runtime": 753.7133, |
|
"eval_samples_per_second": 20.02, |
|
"eval_steps_per_second": 2.504, |
|
"eval_wer": 1.0026273598995386, |
|
"step": 59800 |
|
}, |
|
{ |
|
"epoch": 10.84, |
|
"eval_loss": 0.1591554433107376, |
|
"eval_runtime": 609.7911, |
|
"eval_samples_per_second": 24.745, |
|
"eval_steps_per_second": 3.095, |
|
"eval_wer": 0.9991648531177801, |
|
"step": 59900 |
|
}, |
|
{ |
|
"epoch": 10.85, |
|
"learning_rate": 8.35027905848095e-05, |
|
"loss": 0.0671, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 10.85, |
|
"eval_loss": 0.15896911919116974, |
|
"eval_runtime": 595.2504, |
|
"eval_samples_per_second": 25.349, |
|
"eval_steps_per_second": 3.17, |
|
"eval_wer": 1.0003596617959924, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 10.87, |
|
"eval_loss": 0.15851779282093048, |
|
"eval_runtime": 608.3387, |
|
"eval_samples_per_second": 24.804, |
|
"eval_steps_per_second": 3.102, |
|
"eval_wer": 1.0060106191669258, |
|
"step": 60100 |
|
}, |
|
{ |
|
"epoch": 10.89, |
|
"eval_loss": 0.15786558389663696, |
|
"eval_runtime": 582.1448, |
|
"eval_samples_per_second": 25.92, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0063337051870547, |
|
"step": 60200 |
|
}, |
|
{ |
|
"epoch": 10.91, |
|
"eval_loss": 0.1582275778055191, |
|
"eval_runtime": 580.089, |
|
"eval_samples_per_second": 26.012, |
|
"eval_steps_per_second": 3.253, |
|
"eval_wer": 0.9948793913790897, |
|
"step": 60300 |
|
}, |
|
{ |
|
"epoch": 10.93, |
|
"eval_loss": 0.15619191527366638, |
|
"eval_runtime": 591.1367, |
|
"eval_samples_per_second": 25.525, |
|
"eval_steps_per_second": 3.192, |
|
"eval_wer": 1.0003962375718563, |
|
"step": 60400 |
|
}, |
|
{ |
|
"epoch": 10.94, |
|
"learning_rate": 8.168284396991022e-05, |
|
"loss": 0.0661, |
|
"step": 60500 |
|
}, |
|
{ |
|
"epoch": 10.94, |
|
"eval_loss": 0.15603141486644745, |
|
"eval_runtime": 709.5495, |
|
"eval_samples_per_second": 21.266, |
|
"eval_steps_per_second": 2.659, |
|
"eval_wer": 0.9949952146693245, |
|
"step": 60500 |
|
}, |
|
{ |
|
"epoch": 10.96, |
|
"eval_loss": 0.1564040631055832, |
|
"eval_runtime": 794.2132, |
|
"eval_samples_per_second": 18.999, |
|
"eval_steps_per_second": 2.376, |
|
"eval_wer": 0.9989819742384619, |
|
"step": 60600 |
|
}, |
|
{ |
|
"epoch": 10.98, |
|
"eval_loss": 0.15524810552597046, |
|
"eval_runtime": 598.5085, |
|
"eval_samples_per_second": 25.211, |
|
"eval_steps_per_second": 3.153, |
|
"eval_wer": 0.9981834031321056, |
|
"step": 60700 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_loss": 0.15955734252929688, |
|
"eval_runtime": 587.4842, |
|
"eval_samples_per_second": 25.684, |
|
"eval_steps_per_second": 3.212, |
|
"eval_wer": 1.0018287887931823, |
|
"step": 60800 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"eval_loss": 0.16182269155979156, |
|
"eval_runtime": 1030.4887, |
|
"eval_samples_per_second": 14.643, |
|
"eval_steps_per_second": 1.831, |
|
"eval_wer": 0.9904720103875203, |
|
"step": 60900 |
|
}, |
|
{ |
|
"epoch": 11.03, |
|
"learning_rate": 7.987017714147051e-05, |
|
"loss": 0.0634, |
|
"step": 61000 |
|
}, |
|
{ |
|
"epoch": 11.03, |
|
"eval_loss": 0.16515201330184937, |
|
"eval_runtime": 607.7817, |
|
"eval_samples_per_second": 24.826, |
|
"eval_steps_per_second": 3.105, |
|
"eval_wer": 0.9889663076144669, |
|
"step": 61000 |
|
}, |
|
{ |
|
"epoch": 11.05, |
|
"eval_loss": 0.16492097079753876, |
|
"eval_runtime": 598.9216, |
|
"eval_samples_per_second": 25.194, |
|
"eval_steps_per_second": 3.151, |
|
"eval_wer": 0.988643221594338, |
|
"step": 61100 |
|
}, |
|
{ |
|
"epoch": 11.07, |
|
"eval_loss": 0.16676683723926544, |
|
"eval_runtime": 595.7546, |
|
"eval_samples_per_second": 25.328, |
|
"eval_steps_per_second": 3.167, |
|
"eval_wer": 0.9870338874563377, |
|
"step": 61200 |
|
}, |
|
{ |
|
"epoch": 11.09, |
|
"eval_loss": 0.16629168391227722, |
|
"eval_runtime": 654.8399, |
|
"eval_samples_per_second": 23.042, |
|
"eval_steps_per_second": 2.882, |
|
"eval_wer": 0.9921179203013843, |
|
"step": 61300 |
|
}, |
|
{ |
|
"epoch": 11.11, |
|
"eval_loss": 0.1650213599205017, |
|
"eval_runtime": 773.1318, |
|
"eval_samples_per_second": 19.517, |
|
"eval_steps_per_second": 2.441, |
|
"eval_wer": 0.9918923696835585, |
|
"step": 61400 |
|
}, |
|
{ |
|
"epoch": 11.13, |
|
"learning_rate": 7.805023052657121e-05, |
|
"loss": 0.0587, |
|
"step": 61500 |
|
}, |
|
{ |
|
"epoch": 11.13, |
|
"eval_loss": 0.16744260489940643, |
|
"eval_runtime": 596.1745, |
|
"eval_samples_per_second": 25.31, |
|
"eval_steps_per_second": 3.165, |
|
"eval_wer": 0.9830715117377761, |
|
"step": 61500 |
|
}, |
|
{ |
|
"epoch": 11.14, |
|
"eval_loss": 0.16329726576805115, |
|
"eval_runtime": 590.0495, |
|
"eval_samples_per_second": 25.572, |
|
"eval_steps_per_second": 3.198, |
|
"eval_wer": 0.9792981108611767, |
|
"step": 61600 |
|
}, |
|
{ |
|
"epoch": 11.16, |
|
"eval_loss": 0.1665409654378891, |
|
"eval_runtime": 872.8813, |
|
"eval_samples_per_second": 17.286, |
|
"eval_steps_per_second": 2.162, |
|
"eval_wer": 0.9781093981456082, |
|
"step": 61700 |
|
}, |
|
{ |
|
"epoch": 11.18, |
|
"eval_loss": 0.16423752903938293, |
|
"eval_runtime": 772.8941, |
|
"eval_samples_per_second": 19.523, |
|
"eval_steps_per_second": 2.441, |
|
"eval_wer": 0.982053485976238, |
|
"step": 61800 |
|
}, |
|
{ |
|
"epoch": 11.2, |
|
"eval_loss": 0.16376256942749023, |
|
"eval_runtime": 580.3017, |
|
"eval_samples_per_second": 26.002, |
|
"eval_steps_per_second": 3.252, |
|
"eval_wer": 0.9796577726571691, |
|
"step": 61900 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"learning_rate": 7.623028391167192e-05, |
|
"loss": 0.0581, |
|
"step": 62000 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"eval_loss": 0.1627783179283142, |
|
"eval_runtime": 581.6544, |
|
"eval_samples_per_second": 25.942, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 0.9726778954298568, |
|
"step": 62000 |
|
}, |
|
{ |
|
"epoch": 11.23, |
|
"eval_loss": 0.16605274379253387, |
|
"eval_runtime": 737.7411, |
|
"eval_samples_per_second": 20.453, |
|
"eval_steps_per_second": 2.558, |
|
"eval_wer": 0.9796394847692373, |
|
"step": 62100 |
|
}, |
|
{ |
|
"epoch": 11.25, |
|
"eval_loss": 0.164078027009964, |
|
"eval_runtime": 696.1898, |
|
"eval_samples_per_second": 21.674, |
|
"eval_steps_per_second": 2.71, |
|
"eval_wer": 0.9829617844101851, |
|
"step": 62200 |
|
}, |
|
{ |
|
"epoch": 11.27, |
|
"eval_loss": 0.1601402908563614, |
|
"eval_runtime": 593.4458, |
|
"eval_samples_per_second": 25.426, |
|
"eval_steps_per_second": 3.18, |
|
"eval_wer": 0.9866620337350572, |
|
"step": 62300 |
|
}, |
|
{ |
|
"epoch": 11.29, |
|
"eval_loss": 0.16263510286808014, |
|
"eval_runtime": 599.2385, |
|
"eval_samples_per_second": 25.18, |
|
"eval_steps_per_second": 3.149, |
|
"eval_wer": 0.9756832050133197, |
|
"step": 62400 |
|
}, |
|
{ |
|
"epoch": 11.31, |
|
"learning_rate": 7.441033729677263e-05, |
|
"loss": 0.0584, |
|
"step": 62500 |
|
}, |
|
{ |
|
"epoch": 11.31, |
|
"eval_loss": 0.16319765150547028, |
|
"eval_runtime": 819.3596, |
|
"eval_samples_per_second": 18.416, |
|
"eval_steps_per_second": 2.303, |
|
"eval_wer": 1.0013654956322429, |
|
"step": 62500 |
|
}, |
|
{ |
|
"epoch": 11.32, |
|
"eval_loss": 0.16259542107582092, |
|
"eval_runtime": 772.2475, |
|
"eval_samples_per_second": 19.539, |
|
"eval_steps_per_second": 2.444, |
|
"eval_wer": 1.005169376322062, |
|
"step": 62600 |
|
}, |
|
{ |
|
"epoch": 11.34, |
|
"eval_loss": 0.1586335301399231, |
|
"eval_runtime": 596.9725, |
|
"eval_samples_per_second": 25.276, |
|
"eval_steps_per_second": 3.161, |
|
"eval_wer": 1.0098388837073207, |
|
"step": 62700 |
|
}, |
|
{ |
|
"epoch": 11.36, |
|
"eval_loss": 0.15968169271945953, |
|
"eval_runtime": 581.6566, |
|
"eval_samples_per_second": 25.941, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.015063123693178, |
|
"step": 62800 |
|
}, |
|
{ |
|
"epoch": 11.38, |
|
"eval_loss": 0.162418931722641, |
|
"eval_runtime": 736.848, |
|
"eval_samples_per_second": 20.478, |
|
"eval_steps_per_second": 2.561, |
|
"eval_wer": 1.0054254067531074, |
|
"step": 62900 |
|
}, |
|
{ |
|
"epoch": 11.4, |
|
"learning_rate": 7.259039068187334e-05, |
|
"loss": 0.0589, |
|
"step": 63000 |
|
}, |
|
{ |
|
"epoch": 11.4, |
|
"eval_loss": 0.16180075705051422, |
|
"eval_runtime": 774.1276, |
|
"eval_samples_per_second": 19.492, |
|
"eval_steps_per_second": 2.438, |
|
"eval_wer": 1.0017800210920307, |
|
"step": 63000 |
|
}, |
|
{ |
|
"epoch": 11.41, |
|
"eval_loss": 0.16354435682296753, |
|
"eval_runtime": 594.6962, |
|
"eval_samples_per_second": 25.373, |
|
"eval_steps_per_second": 3.173, |
|
"eval_wer": 1.0031699005748493, |
|
"step": 63100 |
|
}, |
|
{ |
|
"epoch": 11.43, |
|
"eval_loss": 0.16535265743732452, |
|
"eval_runtime": 592.2376, |
|
"eval_samples_per_second": 25.478, |
|
"eval_steps_per_second": 3.186, |
|
"eval_wer": 1.0141974969977383, |
|
"step": 63200 |
|
}, |
|
{ |
|
"epoch": 11.45, |
|
"eval_loss": 0.16461621224880219, |
|
"eval_runtime": 716.9918, |
|
"eval_samples_per_second": 21.045, |
|
"eval_steps_per_second": 2.632, |
|
"eval_wer": 1.00310894094841, |
|
"step": 63300 |
|
}, |
|
{ |
|
"epoch": 11.47, |
|
"eval_loss": 0.16176651418209076, |
|
"eval_runtime": 647.4, |
|
"eval_samples_per_second": 23.307, |
|
"eval_steps_per_second": 2.915, |
|
"eval_wer": 1.011753015977518, |
|
"step": 63400 |
|
}, |
|
{ |
|
"epoch": 11.49, |
|
"learning_rate": 7.077044406697403e-05, |
|
"loss": 0.0579, |
|
"step": 63500 |
|
}, |
|
{ |
|
"epoch": 11.49, |
|
"eval_loss": 0.16339966654777527, |
|
"eval_runtime": 586.1423, |
|
"eval_samples_per_second": 25.743, |
|
"eval_steps_per_second": 3.219, |
|
"eval_wer": 1.021756490676225, |
|
"step": 63500 |
|
}, |
|
{ |
|
"epoch": 11.51, |
|
"eval_loss": 0.16159561276435852, |
|
"eval_runtime": 580.4665, |
|
"eval_samples_per_second": 25.995, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0179221301731862, |
|
"step": 63600 |
|
}, |
|
{ |
|
"epoch": 11.52, |
|
"eval_loss": 0.16033950448036194, |
|
"eval_runtime": 1050.4902, |
|
"eval_samples_per_second": 14.364, |
|
"eval_steps_per_second": 1.796, |
|
"eval_wer": 1.0035539462214176, |
|
"step": 63700 |
|
}, |
|
{ |
|
"epoch": 11.54, |
|
"eval_loss": 0.16100841760635376, |
|
"eval_runtime": 798.7889, |
|
"eval_samples_per_second": 18.89, |
|
"eval_steps_per_second": 2.362, |
|
"eval_wer": 1.0150143559920264, |
|
"step": 63800 |
|
}, |
|
{ |
|
"epoch": 11.56, |
|
"eval_loss": 0.16050441563129425, |
|
"eval_runtime": 586.8618, |
|
"eval_samples_per_second": 25.711, |
|
"eval_steps_per_second": 3.215, |
|
"eval_wer": 1.0285047213230678, |
|
"step": 63900 |
|
}, |
|
{ |
|
"epoch": 11.58, |
|
"learning_rate": 6.895049745207474e-05, |
|
"loss": 0.0572, |
|
"step": 64000 |
|
}, |
|
{ |
|
"epoch": 11.58, |
|
"eval_loss": 0.16212163865566254, |
|
"eval_runtime": 581.4798, |
|
"eval_samples_per_second": 25.949, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0261333918545748, |
|
"step": 64000 |
|
}, |
|
{ |
|
"epoch": 11.6, |
|
"eval_loss": 0.16254810988903046, |
|
"eval_runtime": 605.5049, |
|
"eval_samples_per_second": 24.92, |
|
"eval_steps_per_second": 3.116, |
|
"eval_wer": 1.0251580378315441, |
|
"step": 64100 |
|
}, |
|
{ |
|
"epoch": 11.61, |
|
"eval_loss": 0.1677384078502655, |
|
"eval_runtime": 890.1937, |
|
"eval_samples_per_second": 16.95, |
|
"eval_steps_per_second": 2.12, |
|
"eval_wer": 1.0256761946562791, |
|
"step": 64200 |
|
}, |
|
{ |
|
"epoch": 11.63, |
|
"eval_loss": 0.16564221680164337, |
|
"eval_runtime": 584.838, |
|
"eval_samples_per_second": 25.8, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.024341178837256, |
|
"step": 64300 |
|
}, |
|
{ |
|
"epoch": 11.65, |
|
"eval_loss": 0.1668614149093628, |
|
"eval_runtime": 599.9212, |
|
"eval_samples_per_second": 25.152, |
|
"eval_steps_per_second": 3.145, |
|
"eval_wer": 1.02702340240059, |
|
"step": 64400 |
|
}, |
|
{ |
|
"epoch": 11.67, |
|
"learning_rate": 6.713419073040524e-05, |
|
"loss": 0.0592, |
|
"step": 64500 |
|
}, |
|
{ |
|
"epoch": 11.67, |
|
"eval_loss": 0.16048605740070343, |
|
"eval_runtime": 1005.1834, |
|
"eval_samples_per_second": 15.011, |
|
"eval_steps_per_second": 1.877, |
|
"eval_wer": 1.0305163889955682, |
|
"step": 64500 |
|
}, |
|
{ |
|
"epoch": 11.69, |
|
"eval_loss": 0.16325299441814423, |
|
"eval_runtime": 666.8824, |
|
"eval_samples_per_second": 22.626, |
|
"eval_steps_per_second": 2.83, |
|
"eval_wer": 1.0277244381046433, |
|
"step": 64600 |
|
}, |
|
{ |
|
"epoch": 11.7, |
|
"eval_loss": 0.16055461764335632, |
|
"eval_runtime": 580.9411, |
|
"eval_samples_per_second": 25.973, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0175563724145498, |
|
"step": 64700 |
|
}, |
|
{ |
|
"epoch": 11.72, |
|
"eval_loss": 0.1617630422115326, |
|
"eval_runtime": 581.6126, |
|
"eval_samples_per_second": 25.943, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0248776235499228, |
|
"step": 64800 |
|
}, |
|
{ |
|
"epoch": 11.74, |
|
"eval_loss": 0.16090288758277893, |
|
"eval_runtime": 1362.575, |
|
"eval_samples_per_second": 11.074, |
|
"eval_steps_per_second": 1.385, |
|
"eval_wer": 1.01133849051773, |
|
"step": 64900 |
|
}, |
|
{ |
|
"epoch": 11.76, |
|
"learning_rate": 6.531424411550595e-05, |
|
"loss": 0.0595, |
|
"step": 65000 |
|
}, |
|
{ |
|
"epoch": 11.76, |
|
"eval_loss": 0.16091392934322357, |
|
"eval_runtime": 585.1401, |
|
"eval_samples_per_second": 25.787, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0254079722999458, |
|
"step": 65000 |
|
}, |
|
{ |
|
"epoch": 11.78, |
|
"eval_loss": 0.16618193686008453, |
|
"eval_runtime": 582.6728, |
|
"eval_samples_per_second": 25.896, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0274927915241736, |
|
"step": 65100 |
|
}, |
|
{ |
|
"epoch": 11.79, |
|
"eval_loss": 0.16519132256507874, |
|
"eval_runtime": 581.4475, |
|
"eval_samples_per_second": 25.951, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.0163676596989815, |
|
"step": 65200 |
|
}, |
|
{ |
|
"epoch": 11.81, |
|
"eval_loss": 0.16376902163028717, |
|
"eval_runtime": 743.8564, |
|
"eval_samples_per_second": 20.285, |
|
"eval_steps_per_second": 2.537, |
|
"eval_wer": 1.026614972903446, |
|
"step": 65300 |
|
}, |
|
{ |
|
"epoch": 11.83, |
|
"eval_loss": 0.1588725447654724, |
|
"eval_runtime": 656.9651, |
|
"eval_samples_per_second": 22.968, |
|
"eval_steps_per_second": 2.872, |
|
"eval_wer": 1.0273952561218704, |
|
"step": 65400 |
|
}, |
|
{ |
|
"epoch": 11.85, |
|
"learning_rate": 6.349429750060664e-05, |
|
"loss": 0.0588, |
|
"step": 65500 |
|
}, |
|
{ |
|
"epoch": 11.85, |
|
"eval_loss": 0.16070173680782318, |
|
"eval_runtime": 596.2298, |
|
"eval_samples_per_second": 25.307, |
|
"eval_steps_per_second": 3.165, |
|
"eval_wer": 1.0135635168827686, |
|
"step": 65500 |
|
}, |
|
{ |
|
"epoch": 11.87, |
|
"eval_loss": 0.15919756889343262, |
|
"eval_runtime": 582.5632, |
|
"eval_samples_per_second": 25.901, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0135818047707004, |
|
"step": 65600 |
|
}, |
|
{ |
|
"epoch": 11.88, |
|
"eval_loss": 0.15812398493289948, |
|
"eval_runtime": 885.713, |
|
"eval_samples_per_second": 17.036, |
|
"eval_steps_per_second": 2.13, |
|
"eval_wer": 1.018281791969179, |
|
"step": 65700 |
|
}, |
|
{ |
|
"epoch": 11.9, |
|
"eval_loss": 0.15873989462852478, |
|
"eval_runtime": 753.9732, |
|
"eval_samples_per_second": 20.013, |
|
"eval_steps_per_second": 2.503, |
|
"eval_wer": 1.0132891985637913, |
|
"step": 65800 |
|
}, |
|
{ |
|
"epoch": 11.92, |
|
"eval_loss": 0.15961608290672302, |
|
"eval_runtime": 581.7374, |
|
"eval_samples_per_second": 25.938, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0169894478886634, |
|
"step": 65900 |
|
}, |
|
{ |
|
"epoch": 11.94, |
|
"learning_rate": 6.167435088570735e-05, |
|
"loss": 0.0558, |
|
"step": 66000 |
|
}, |
|
{ |
|
"epoch": 11.94, |
|
"eval_loss": 0.15900225937366486, |
|
"eval_runtime": 581.5784, |
|
"eval_samples_per_second": 25.945, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.016099437342648, |
|
"step": 66000 |
|
}, |
|
{ |
|
"epoch": 11.96, |
|
"eval_loss": 0.15970025956630707, |
|
"eval_runtime": 777.4608, |
|
"eval_samples_per_second": 19.408, |
|
"eval_steps_per_second": 2.427, |
|
"eval_wer": 1.0193485854318685, |
|
"step": 66100 |
|
}, |
|
{ |
|
"epoch": 11.98, |
|
"eval_loss": 0.15903662145137787, |
|
"eval_runtime": 626.8518, |
|
"eval_samples_per_second": 24.071, |
|
"eval_steps_per_second": 3.01, |
|
"eval_wer": 1.019287625805429, |
|
"step": 66200 |
|
}, |
|
{ |
|
"epoch": 11.99, |
|
"eval_loss": 0.16078583896160126, |
|
"eval_runtime": 597.6499, |
|
"eval_samples_per_second": 25.247, |
|
"eval_steps_per_second": 3.157, |
|
"eval_wer": 1.0242131636217333, |
|
"step": 66300 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"eval_loss": 0.16416209936141968, |
|
"eval_runtime": 583.6843, |
|
"eval_samples_per_second": 25.851, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.0231036984205362, |
|
"step": 66400 |
|
}, |
|
{ |
|
"epoch": 12.03, |
|
"learning_rate": 5.985440427080805e-05, |
|
"loss": 0.0555, |
|
"step": 66500 |
|
}, |
|
{ |
|
"epoch": 12.03, |
|
"eval_loss": 0.16788017749786377, |
|
"eval_runtime": 707.5448, |
|
"eval_samples_per_second": 21.326, |
|
"eval_steps_per_second": 2.667, |
|
"eval_wer": 1.0167882811214133, |
|
"step": 66500 |
|
}, |
|
{ |
|
"epoch": 12.05, |
|
"eval_loss": 0.16742467880249023, |
|
"eval_runtime": 622.7757, |
|
"eval_samples_per_second": 24.229, |
|
"eval_steps_per_second": 3.03, |
|
"eval_wer": 1.0083331809342673, |
|
"step": 66600 |
|
}, |
|
{ |
|
"epoch": 12.07, |
|
"eval_loss": 0.16581884026527405, |
|
"eval_runtime": 602.3727, |
|
"eval_samples_per_second": 25.049, |
|
"eval_steps_per_second": 3.133, |
|
"eval_wer": 1.006912821638229, |
|
"step": 66700 |
|
}, |
|
{ |
|
"epoch": 12.08, |
|
"eval_loss": 0.16606904566287994, |
|
"eval_runtime": 608.0454, |
|
"eval_samples_per_second": 24.816, |
|
"eval_steps_per_second": 3.103, |
|
"eval_wer": 1.0133867339660942, |
|
"step": 66800 |
|
}, |
|
{ |
|
"epoch": 12.1, |
|
"eval_loss": 0.16823889315128326, |
|
"eval_runtime": 947.3259, |
|
"eval_samples_per_second": 15.928, |
|
"eval_steps_per_second": 1.992, |
|
"eval_wer": 1.0274318318977342, |
|
"step": 66900 |
|
}, |
|
{ |
|
"epoch": 12.12, |
|
"learning_rate": 5.8034457655908755e-05, |
|
"loss": 0.0508, |
|
"step": 67000 |
|
}, |
|
{ |
|
"epoch": 12.12, |
|
"eval_loss": 0.1702161282300949, |
|
"eval_runtime": 601.9908, |
|
"eval_samples_per_second": 25.065, |
|
"eval_steps_per_second": 3.135, |
|
"eval_wer": 1.0219271776302554, |
|
"step": 67000 |
|
}, |
|
{ |
|
"epoch": 12.14, |
|
"eval_loss": 0.16944070160388947, |
|
"eval_runtime": 582.5035, |
|
"eval_samples_per_second": 25.904, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.021860122041172, |
|
"step": 67100 |
|
}, |
|
{ |
|
"epoch": 12.16, |
|
"eval_loss": 0.16666612029075623, |
|
"eval_runtime": 581.5026, |
|
"eval_samples_per_second": 25.948, |
|
"eval_steps_per_second": 3.245, |
|
"eval_wer": 1.023640143133203, |
|
"step": 67200 |
|
}, |
|
{ |
|
"epoch": 12.17, |
|
"eval_loss": 0.16717979311943054, |
|
"eval_runtime": 586.3236, |
|
"eval_samples_per_second": 25.735, |
|
"eval_steps_per_second": 3.218, |
|
"eval_wer": 1.0253226288229307, |
|
"step": 67300 |
|
}, |
|
{ |
|
"epoch": 12.19, |
|
"eval_loss": 0.16397833824157715, |
|
"eval_runtime": 754.9429, |
|
"eval_samples_per_second": 19.987, |
|
"eval_steps_per_second": 2.5, |
|
"eval_wer": 1.021457788506672, |
|
"step": 67400 |
|
}, |
|
{ |
|
"epoch": 12.21, |
|
"learning_rate": 5.621451104100946e-05, |
|
"loss": 0.0513, |
|
"step": 67500 |
|
}, |
|
{ |
|
"epoch": 12.21, |
|
"eval_loss": 0.16485707461833954, |
|
"eval_runtime": 604.5571, |
|
"eval_samples_per_second": 24.959, |
|
"eval_steps_per_second": 3.121, |
|
"eval_wer": 1.024237547472309, |
|
"step": 67500 |
|
}, |
|
{ |
|
"epoch": 12.23, |
|
"eval_loss": 0.16873668134212494, |
|
"eval_runtime": 594.5739, |
|
"eval_samples_per_second": 25.378, |
|
"eval_steps_per_second": 3.174, |
|
"eval_wer": 1.026224831294234, |
|
"step": 67600 |
|
}, |
|
{ |
|
"epoch": 12.25, |
|
"eval_loss": 0.16546061635017395, |
|
"eval_runtime": 1060.8443, |
|
"eval_samples_per_second": 14.224, |
|
"eval_steps_per_second": 1.779, |
|
"eval_wer": 1.0231036984205362, |
|
"step": 67700 |
|
}, |
|
{ |
|
"epoch": 12.26, |
|
"eval_loss": 0.1691717505455017, |
|
"eval_runtime": 598.0013, |
|
"eval_samples_per_second": 25.232, |
|
"eval_steps_per_second": 3.156, |
|
"eval_wer": 1.0176112360783454, |
|
"step": 67800 |
|
}, |
|
{ |
|
"epoch": 12.28, |
|
"eval_loss": 0.16749083995819092, |
|
"eval_runtime": 584.068, |
|
"eval_samples_per_second": 25.834, |
|
"eval_steps_per_second": 3.231, |
|
"eval_wer": 1.0201654444261565, |
|
"step": 67900 |
|
}, |
|
{ |
|
"epoch": 12.3, |
|
"learning_rate": 5.439456442611016e-05, |
|
"loss": 0.0519, |
|
"step": 68000 |
|
}, |
|
{ |
|
"epoch": 12.3, |
|
"eval_loss": 0.16435594856739044, |
|
"eval_runtime": 581.2292, |
|
"eval_samples_per_second": 25.961, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0240973403314984, |
|
"step": 68000 |
|
}, |
|
{ |
|
"epoch": 12.32, |
|
"eval_loss": 0.16505275666713715, |
|
"eval_runtime": 865.456, |
|
"eval_samples_per_second": 17.435, |
|
"eval_steps_per_second": 2.18, |
|
"eval_wer": 1.029717817889212, |
|
"step": 68100 |
|
}, |
|
{ |
|
"epoch": 12.34, |
|
"eval_loss": 0.16610455513000488, |
|
"eval_runtime": 617.3975, |
|
"eval_samples_per_second": 24.44, |
|
"eval_steps_per_second": 3.056, |
|
"eval_wer": 1.0287363679035375, |
|
"step": 68200 |
|
}, |
|
{ |
|
"epoch": 12.36, |
|
"eval_loss": 0.16653628647327423, |
|
"eval_runtime": 579.7196, |
|
"eval_samples_per_second": 26.028, |
|
"eval_steps_per_second": 3.255, |
|
"eval_wer": 1.0256761946562791, |
|
"step": 68300 |
|
}, |
|
{ |
|
"epoch": 12.37, |
|
"eval_loss": 0.16854335367679596, |
|
"eval_runtime": 582.7632, |
|
"eval_samples_per_second": 25.892, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0232743853745665, |
|
"step": 68400 |
|
}, |
|
{ |
|
"epoch": 12.39, |
|
"learning_rate": 5.258189759767046e-05, |
|
"loss": 0.0522, |
|
"step": 68500 |
|
}, |
|
{ |
|
"epoch": 12.39, |
|
"eval_loss": 0.1635940819978714, |
|
"eval_runtime": 1242.3531, |
|
"eval_samples_per_second": 12.146, |
|
"eval_steps_per_second": 1.519, |
|
"eval_wer": 1.017733155331224, |
|
"step": 68500 |
|
}, |
|
{ |
|
"epoch": 12.41, |
|
"eval_loss": 0.17086556553840637, |
|
"eval_runtime": 604.527, |
|
"eval_samples_per_second": 24.96, |
|
"eval_steps_per_second": 3.121, |
|
"eval_wer": 1.0199947574721262, |
|
"step": 68600 |
|
}, |
|
{ |
|
"epoch": 12.43, |
|
"eval_loss": 0.16842861473560333, |
|
"eval_runtime": 594.3258, |
|
"eval_samples_per_second": 25.388, |
|
"eval_steps_per_second": 3.175, |
|
"eval_wer": 1.0164347152880646, |
|
"step": 68700 |
|
}, |
|
{ |
|
"epoch": 12.45, |
|
"eval_loss": 0.16664543747901917, |
|
"eval_runtime": 582.5029, |
|
"eval_samples_per_second": 25.904, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0118810311930408, |
|
"step": 68800 |
|
}, |
|
{ |
|
"epoch": 12.46, |
|
"eval_loss": 0.16832029819488525, |
|
"eval_runtime": 794.8021, |
|
"eval_samples_per_second": 18.985, |
|
"eval_steps_per_second": 2.374, |
|
"eval_wer": 1.0136427643971397, |
|
"step": 68900 |
|
}, |
|
{ |
|
"epoch": 12.48, |
|
"learning_rate": 5.076195098277117e-05, |
|
"loss": 0.05, |
|
"step": 69000 |
|
}, |
|
{ |
|
"epoch": 12.48, |
|
"eval_loss": 0.16963930428028107, |
|
"eval_runtime": 582.3733, |
|
"eval_samples_per_second": 25.909, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.012703986149973, |
|
"step": 69000 |
|
}, |
|
{ |
|
"epoch": 12.5, |
|
"eval_loss": 0.17076294124126434, |
|
"eval_runtime": 586.0869, |
|
"eval_samples_per_second": 25.745, |
|
"eval_steps_per_second": 3.22, |
|
"eval_wer": 1.01836103948355, |
|
"step": 69100 |
|
}, |
|
{ |
|
"epoch": 12.52, |
|
"eval_loss": 0.1653919816017151, |
|
"eval_runtime": 580.9443, |
|
"eval_samples_per_second": 25.973, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0282486908920223, |
|
"step": 69200 |
|
}, |
|
{ |
|
"epoch": 12.54, |
|
"eval_loss": 0.17003265023231506, |
|
"eval_runtime": 864.4381, |
|
"eval_samples_per_second": 17.455, |
|
"eval_steps_per_second": 2.183, |
|
"eval_wer": 1.0234633602165286, |
|
"step": 69300 |
|
}, |
|
{ |
|
"epoch": 12.55, |
|
"eval_loss": 0.1688261330127716, |
|
"eval_runtime": 728.1606, |
|
"eval_samples_per_second": 20.722, |
|
"eval_steps_per_second": 2.591, |
|
"eval_wer": 1.0257188663947867, |
|
"step": 69400 |
|
}, |
|
{ |
|
"epoch": 12.57, |
|
"learning_rate": 4.894200436787187e-05, |
|
"loss": 0.0513, |
|
"step": 69500 |
|
}, |
|
{ |
|
"epoch": 12.57, |
|
"eval_loss": 0.16455566883087158, |
|
"eval_runtime": 591.0272, |
|
"eval_samples_per_second": 25.53, |
|
"eval_steps_per_second": 3.193, |
|
"eval_wer": 1.0273525843833629, |
|
"step": 69500 |
|
}, |
|
{ |
|
"epoch": 12.59, |
|
"eval_loss": 0.16600140929222107, |
|
"eval_runtime": 581.0392, |
|
"eval_samples_per_second": 25.969, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0246520729320971, |
|
"step": 69600 |
|
}, |
|
{ |
|
"epoch": 12.61, |
|
"eval_loss": 0.16570237278938293, |
|
"eval_runtime": 845.5309, |
|
"eval_samples_per_second": 17.846, |
|
"eval_steps_per_second": 2.232, |
|
"eval_wer": 1.0187511810927623, |
|
"step": 69700 |
|
}, |
|
{ |
|
"epoch": 12.63, |
|
"eval_loss": 0.1653689593076706, |
|
"eval_runtime": 623.5969, |
|
"eval_samples_per_second": 24.197, |
|
"eval_steps_per_second": 3.026, |
|
"eval_wer": 1.008668458879684, |
|
"step": 69800 |
|
}, |
|
{ |
|
"epoch": 12.64, |
|
"eval_loss": 0.1681143045425415, |
|
"eval_runtime": 585.1239, |
|
"eval_samples_per_second": 25.788, |
|
"eval_steps_per_second": 3.225, |
|
"eval_wer": 1.0145876386069506, |
|
"step": 69900 |
|
}, |
|
{ |
|
"epoch": 12.66, |
|
"learning_rate": 4.712205775297258e-05, |
|
"loss": 0.0512, |
|
"step": 70000 |
|
}, |
|
{ |
|
"epoch": 12.66, |
|
"eval_loss": 0.16601833701133728, |
|
"eval_runtime": 581.0502, |
|
"eval_samples_per_second": 25.968, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.018458574885853, |
|
"step": 70000 |
|
}, |
|
{ |
|
"epoch": 12.68, |
|
"eval_loss": 0.16897162795066833, |
|
"eval_runtime": 678.6995, |
|
"eval_samples_per_second": 22.232, |
|
"eval_steps_per_second": 2.78, |
|
"eval_wer": 1.0214212127308084, |
|
"step": 70100 |
|
}, |
|
{ |
|
"epoch": 12.7, |
|
"eval_loss": 0.16828937828540802, |
|
"eval_runtime": 648.0173, |
|
"eval_samples_per_second": 23.285, |
|
"eval_steps_per_second": 2.912, |
|
"eval_wer": 1.015995805977701, |
|
"step": 70200 |
|
}, |
|
{ |
|
"epoch": 12.72, |
|
"eval_loss": 0.16954827308654785, |
|
"eval_runtime": 587.6953, |
|
"eval_samples_per_second": 25.675, |
|
"eval_steps_per_second": 3.211, |
|
"eval_wer": 1.019811878592808, |
|
"step": 70300 |
|
}, |
|
{ |
|
"epoch": 12.74, |
|
"eval_loss": 0.1666439175605774, |
|
"eval_runtime": 588.0923, |
|
"eval_samples_per_second": 25.658, |
|
"eval_steps_per_second": 3.209, |
|
"eval_wer": 1.0192693379174973, |
|
"step": 70400 |
|
}, |
|
{ |
|
"epoch": 12.75, |
|
"learning_rate": 4.530575103130307e-05, |
|
"loss": 0.0484, |
|
"step": 70500 |
|
}, |
|
{ |
|
"epoch": 12.75, |
|
"eval_loss": 0.16543133556842804, |
|
"eval_runtime": 812.0461, |
|
"eval_samples_per_second": 18.581, |
|
"eval_steps_per_second": 2.324, |
|
"eval_wer": 1.0141609212218747, |
|
"step": 70500 |
|
}, |
|
{ |
|
"epoch": 12.77, |
|
"eval_loss": 0.15983402729034424, |
|
"eval_runtime": 628.158, |
|
"eval_samples_per_second": 24.021, |
|
"eval_steps_per_second": 3.004, |
|
"eval_wer": 1.015374017788019, |
|
"step": 70600 |
|
}, |
|
{ |
|
"epoch": 12.79, |
|
"eval_loss": 0.1623169183731079, |
|
"eval_runtime": 586.556, |
|
"eval_samples_per_second": 25.725, |
|
"eval_steps_per_second": 3.217, |
|
"eval_wer": 1.013923178678761, |
|
"step": 70700 |
|
}, |
|
{ |
|
"epoch": 12.81, |
|
"eval_loss": 0.16623294353485107, |
|
"eval_runtime": 590.6252, |
|
"eval_samples_per_second": 25.548, |
|
"eval_steps_per_second": 3.195, |
|
"eval_wer": 1.0180013776875576, |
|
"step": 70800 |
|
}, |
|
{ |
|
"epoch": 12.83, |
|
"eval_loss": 0.16593489050865173, |
|
"eval_runtime": 853.4994, |
|
"eval_samples_per_second": 17.679, |
|
"eval_steps_per_second": 2.211, |
|
"eval_wer": 1.0231646580469755, |
|
"step": 70900 |
|
}, |
|
{ |
|
"epoch": 12.84, |
|
"learning_rate": 4.348580441640378e-05, |
|
"loss": 0.0501, |
|
"step": 71000 |
|
}, |
|
{ |
|
"epoch": 12.84, |
|
"eval_loss": 0.16620078682899475, |
|
"eval_runtime": 581.8553, |
|
"eval_samples_per_second": 25.933, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0202446919405277, |
|
"step": 71000 |
|
}, |
|
{ |
|
"epoch": 12.86, |
|
"eval_loss": 0.16386279463768005, |
|
"eval_runtime": 588.8821, |
|
"eval_samples_per_second": 25.623, |
|
"eval_steps_per_second": 3.204, |
|
"eval_wer": 1.0161299171558678, |
|
"step": 71100 |
|
}, |
|
{ |
|
"epoch": 12.88, |
|
"eval_loss": 0.1666136533021927, |
|
"eval_runtime": 585.387, |
|
"eval_samples_per_second": 25.776, |
|
"eval_steps_per_second": 3.224, |
|
"eval_wer": 1.0151423712075491, |
|
"step": 71200 |
|
}, |
|
{ |
|
"epoch": 12.9, |
|
"eval_loss": 0.16440027952194214, |
|
"eval_runtime": 707.9711, |
|
"eval_samples_per_second": 21.313, |
|
"eval_steps_per_second": 2.665, |
|
"eval_wer": 1.0128624811787152, |
|
"step": 71300 |
|
}, |
|
{ |
|
"epoch": 12.92, |
|
"eval_loss": 0.16417254507541656, |
|
"eval_runtime": 706.7784, |
|
"eval_samples_per_second": 21.349, |
|
"eval_steps_per_second": 2.67, |
|
"eval_wer": 1.0170625994403906, |
|
"step": 71400 |
|
}, |
|
{ |
|
"epoch": 12.93, |
|
"learning_rate": 4.1665857801504485e-05, |
|
"loss": 0.0482, |
|
"step": 71500 |
|
}, |
|
{ |
|
"epoch": 12.93, |
|
"eval_loss": 0.16351790726184845, |
|
"eval_runtime": 590.5254, |
|
"eval_samples_per_second": 25.552, |
|
"eval_steps_per_second": 3.195, |
|
"eval_wer": 1.0162396444834587, |
|
"step": 71500 |
|
}, |
|
{ |
|
"epoch": 12.95, |
|
"eval_loss": 0.1636749505996704, |
|
"eval_runtime": 601.6692, |
|
"eval_samples_per_second": 25.079, |
|
"eval_steps_per_second": 3.136, |
|
"eval_wer": 1.0186170699145956, |
|
"step": 71600 |
|
}, |
|
{ |
|
"epoch": 12.97, |
|
"eval_loss": 0.16393718123435974, |
|
"eval_runtime": 684.7308, |
|
"eval_samples_per_second": 22.036, |
|
"eval_steps_per_second": 2.756, |
|
"eval_wer": 1.014221880848314, |
|
"step": 71700 |
|
}, |
|
{ |
|
"epoch": 12.99, |
|
"eval_loss": 0.1642550379037857, |
|
"eval_runtime": 792.2739, |
|
"eval_samples_per_second": 19.045, |
|
"eval_steps_per_second": 2.382, |
|
"eval_wer": 1.0122345970263895, |
|
"step": 71800 |
|
}, |
|
{ |
|
"epoch": 13.01, |
|
"eval_loss": 0.16787484288215637, |
|
"eval_runtime": 581.9813, |
|
"eval_samples_per_second": 25.927, |
|
"eval_steps_per_second": 3.242, |
|
"eval_wer": 1.0156117603311328, |
|
"step": 71900 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"learning_rate": 3.984955107983499e-05, |
|
"loss": 0.0483, |
|
"step": 72000 |
|
}, |
|
{ |
|
"epoch": 13.02, |
|
"eval_loss": 0.17167212069034576, |
|
"eval_runtime": 581.162, |
|
"eval_samples_per_second": 25.964, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0223721829032633, |
|
"step": 72000 |
|
}, |
|
{ |
|
"epoch": 13.04, |
|
"eval_loss": 0.17421314120292664, |
|
"eval_runtime": 1273.8126, |
|
"eval_samples_per_second": 11.846, |
|
"eval_steps_per_second": 1.481, |
|
"eval_wer": 1.02290862761593, |
|
"step": 72100 |
|
}, |
|
{ |
|
"epoch": 13.06, |
|
"eval_loss": 0.1717776656150818, |
|
"eval_runtime": 638.8652, |
|
"eval_samples_per_second": 23.618, |
|
"eval_steps_per_second": 2.954, |
|
"eval_wer": 1.0236950067969983, |
|
"step": 72200 |
|
}, |
|
{ |
|
"epoch": 13.08, |
|
"eval_loss": 0.17424285411834717, |
|
"eval_runtime": 596.8233, |
|
"eval_samples_per_second": 25.282, |
|
"eval_steps_per_second": 3.162, |
|
"eval_wer": 1.0265723011649384, |
|
"step": 72300 |
|
}, |
|
{ |
|
"epoch": 13.1, |
|
"eval_loss": 0.1735859364271164, |
|
"eval_runtime": 584.6288, |
|
"eval_samples_per_second": 25.81, |
|
"eval_steps_per_second": 3.228, |
|
"eval_wer": 1.0257310583200747, |
|
"step": 72400 |
|
}, |
|
{ |
|
"epoch": 13.12, |
|
"learning_rate": 3.80296044649357e-05, |
|
"loss": 0.0443, |
|
"step": 72500 |
|
}, |
|
{ |
|
"epoch": 13.12, |
|
"eval_loss": 0.17412111163139343, |
|
"eval_runtime": 583.8537, |
|
"eval_samples_per_second": 25.844, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.027541559225325, |
|
"step": 72500 |
|
}, |
|
{ |
|
"epoch": 13.13, |
|
"eval_loss": 0.17448225617408752, |
|
"eval_runtime": 582.1865, |
|
"eval_samples_per_second": 25.918, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0325280566680688, |
|
"step": 72600 |
|
}, |
|
{ |
|
"epoch": 13.15, |
|
"eval_loss": 0.17374877631664276, |
|
"eval_runtime": 591.7623, |
|
"eval_samples_per_second": 25.498, |
|
"eval_steps_per_second": 3.189, |
|
"eval_wer": 1.0295593228604696, |
|
"step": 72700 |
|
}, |
|
{ |
|
"epoch": 13.17, |
|
"eval_loss": 0.17223623394966125, |
|
"eval_runtime": 580.7728, |
|
"eval_samples_per_second": 25.981, |
|
"eval_steps_per_second": 3.249, |
|
"eval_wer": 1.0302847424150985, |
|
"step": 72800 |
|
}, |
|
{ |
|
"epoch": 13.19, |
|
"eval_loss": 0.17018476128578186, |
|
"eval_runtime": 754.3079, |
|
"eval_samples_per_second": 20.004, |
|
"eval_steps_per_second": 2.502, |
|
"eval_wer": 1.0304615253317728, |
|
"step": 72900 |
|
}, |
|
{ |
|
"epoch": 13.21, |
|
"learning_rate": 3.620965785003639e-05, |
|
"loss": 0.0424, |
|
"step": 73000 |
|
}, |
|
{ |
|
"epoch": 13.21, |
|
"eval_loss": 0.17333687841892242, |
|
"eval_runtime": 620.495, |
|
"eval_samples_per_second": 24.318, |
|
"eval_steps_per_second": 3.041, |
|
"eval_wer": 1.0240546685929908, |
|
"step": 73000 |
|
}, |
|
{ |
|
"epoch": 13.22, |
|
"eval_loss": 0.1748303323984146, |
|
"eval_runtime": 581.8368, |
|
"eval_samples_per_second": 25.933, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.0243046030613925, |
|
"step": 73100 |
|
}, |
|
{ |
|
"epoch": 13.24, |
|
"eval_loss": 0.175998255610466, |
|
"eval_runtime": 582.7142, |
|
"eval_samples_per_second": 25.894, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0230732186073164, |
|
"step": 73200 |
|
}, |
|
{ |
|
"epoch": 13.26, |
|
"eval_loss": 0.17454344034194946, |
|
"eval_runtime": 991.8052, |
|
"eval_samples_per_second": 15.214, |
|
"eval_steps_per_second": 1.903, |
|
"eval_wer": 1.0241339161073622, |
|
"step": 73300 |
|
}, |
|
{ |
|
"epoch": 13.28, |
|
"eval_loss": 0.17719770967960358, |
|
"eval_runtime": 699.1737, |
|
"eval_samples_per_second": 21.581, |
|
"eval_steps_per_second": 2.699, |
|
"eval_wer": 1.0217077229750735, |
|
"step": 73400 |
|
}, |
|
{ |
|
"epoch": 13.3, |
|
"learning_rate": 3.4389711235137095e-05, |
|
"loss": 0.0424, |
|
"step": 73500 |
|
}, |
|
{ |
|
"epoch": 13.3, |
|
"eval_loss": 0.17551423609256744, |
|
"eval_runtime": 581.4162, |
|
"eval_samples_per_second": 25.952, |
|
"eval_steps_per_second": 3.246, |
|
"eval_wer": 1.0205677779606566, |
|
"step": 73500 |
|
}, |
|
{ |
|
"epoch": 13.31, |
|
"eval_loss": 0.17427977919578552, |
|
"eval_runtime": 583.119, |
|
"eval_samples_per_second": 25.876, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0241948757338015, |
|
"step": 73600 |
|
}, |
|
{ |
|
"epoch": 13.33, |
|
"eval_loss": 0.1737585812807083, |
|
"eval_runtime": 648.7553, |
|
"eval_samples_per_second": 23.258, |
|
"eval_steps_per_second": 2.909, |
|
"eval_wer": 1.02083600031699, |
|
"step": 73700 |
|
}, |
|
{ |
|
"epoch": 13.35, |
|
"eval_loss": 0.17359158396720886, |
|
"eval_runtime": 582.3603, |
|
"eval_samples_per_second": 25.91, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0248715275872788, |
|
"step": 73800 |
|
}, |
|
{ |
|
"epoch": 13.37, |
|
"eval_loss": 0.17472000420093536, |
|
"eval_runtime": 582.9221, |
|
"eval_samples_per_second": 25.885, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0270599781764538, |
|
"step": 73900 |
|
}, |
|
{ |
|
"epoch": 13.39, |
|
"learning_rate": 3.2569764620237805e-05, |
|
"loss": 0.0437, |
|
"step": 74000 |
|
}, |
|
{ |
|
"epoch": 13.39, |
|
"eval_loss": 0.17074641585350037, |
|
"eval_runtime": 580.5198, |
|
"eval_samples_per_second": 25.992, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0240729564809228, |
|
"step": 74000 |
|
}, |
|
{ |
|
"epoch": 13.4, |
|
"eval_loss": 0.17314904928207397, |
|
"eval_runtime": 1076.3581, |
|
"eval_samples_per_second": 14.019, |
|
"eval_steps_per_second": 1.753, |
|
"eval_wer": 1.0268588114092037, |
|
"step": 74100 |
|
}, |
|
{ |
|
"epoch": 13.42, |
|
"eval_loss": 0.17427843809127808, |
|
"eval_runtime": 629.3424, |
|
"eval_samples_per_second": 23.976, |
|
"eval_steps_per_second": 2.998, |
|
"eval_wer": 1.0290228781478028, |
|
"step": 74200 |
|
}, |
|
{ |
|
"epoch": 13.44, |
|
"eval_loss": 0.17391642928123474, |
|
"eval_runtime": 588.8228, |
|
"eval_samples_per_second": 25.626, |
|
"eval_steps_per_second": 3.205, |
|
"eval_wer": 1.0265783971275824, |
|
"step": 74300 |
|
}, |
|
{ |
|
"epoch": 13.46, |
|
"eval_loss": 0.17630253732204437, |
|
"eval_runtime": 596.5515, |
|
"eval_samples_per_second": 25.294, |
|
"eval_steps_per_second": 3.163, |
|
"eval_wer": 1.024566729455082, |
|
"step": 74400 |
|
}, |
|
{ |
|
"epoch": 13.48, |
|
"learning_rate": 3.074981800533851e-05, |
|
"loss": 0.0443, |
|
"step": 74500 |
|
}, |
|
{ |
|
"epoch": 13.48, |
|
"eval_loss": 0.1723669320344925, |
|
"eval_runtime": 696.4206, |
|
"eval_samples_per_second": 21.667, |
|
"eval_steps_per_second": 2.71, |
|
"eval_wer": 1.020933535719293, |
|
"step": 74500 |
|
}, |
|
{ |
|
"epoch": 13.49, |
|
"eval_loss": 0.17442239820957184, |
|
"eval_runtime": 634.1169, |
|
"eval_samples_per_second": 23.795, |
|
"eval_steps_per_second": 2.976, |
|
"eval_wer": 1.0244204263516272, |
|
"step": 74600 |
|
}, |
|
{ |
|
"epoch": 13.51, |
|
"eval_loss": 0.171742781996727, |
|
"eval_runtime": 588.0795, |
|
"eval_samples_per_second": 25.658, |
|
"eval_steps_per_second": 3.209, |
|
"eval_wer": 1.0231646580469755, |
|
"step": 74700 |
|
}, |
|
{ |
|
"epoch": 13.53, |
|
"eval_loss": 0.17540408670902252, |
|
"eval_runtime": 584.6829, |
|
"eval_samples_per_second": 25.807, |
|
"eval_steps_per_second": 3.227, |
|
"eval_wer": 1.0217016270124297, |
|
"step": 74800 |
|
}, |
|
{ |
|
"epoch": 13.55, |
|
"eval_loss": 0.17214533686637878, |
|
"eval_runtime": 720.7618, |
|
"eval_samples_per_second": 20.935, |
|
"eval_steps_per_second": 2.618, |
|
"eval_wer": 1.023414592515377, |
|
"step": 74900 |
|
}, |
|
{ |
|
"epoch": 13.57, |
|
"learning_rate": 2.8929871390439213e-05, |
|
"loss": 0.0435, |
|
"step": 75000 |
|
}, |
|
{ |
|
"epoch": 13.57, |
|
"eval_loss": 0.17512725293636322, |
|
"eval_runtime": 739.201, |
|
"eval_samples_per_second": 20.413, |
|
"eval_steps_per_second": 2.553, |
|
"eval_wer": 1.0196960553025731, |
|
"step": 75000 |
|
}, |
|
{ |
|
"epoch": 13.59, |
|
"eval_loss": 0.1726856231689453, |
|
"eval_runtime": 583.0039, |
|
"eval_samples_per_second": 25.881, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.0285230092109996, |
|
"step": 75100 |
|
}, |
|
{ |
|
"epoch": 13.6, |
|
"eval_loss": 0.1715420037508011, |
|
"eval_runtime": 601.6364, |
|
"eval_samples_per_second": 25.08, |
|
"eval_steps_per_second": 3.136, |
|
"eval_wer": 1.0220612888084222, |
|
"step": 75200 |
|
}, |
|
{ |
|
"epoch": 13.62, |
|
"eval_loss": 0.17459963262081146, |
|
"eval_runtime": 650.5666, |
|
"eval_samples_per_second": 23.194, |
|
"eval_steps_per_second": 2.901, |
|
"eval_wer": 1.0247130325585365, |
|
"step": 75300 |
|
}, |
|
{ |
|
"epoch": 13.64, |
|
"eval_loss": 0.1712324321269989, |
|
"eval_runtime": 710.0998, |
|
"eval_samples_per_second": 21.249, |
|
"eval_steps_per_second": 2.657, |
|
"eval_wer": 1.0230610266820286, |
|
"step": 75400 |
|
}, |
|
{ |
|
"epoch": 13.66, |
|
"learning_rate": 2.7109924775539916e-05, |
|
"loss": 0.0436, |
|
"step": 75500 |
|
}, |
|
{ |
|
"epoch": 13.66, |
|
"eval_loss": 0.1718807965517044, |
|
"eval_runtime": 593.922, |
|
"eval_samples_per_second": 25.406, |
|
"eval_steps_per_second": 3.177, |
|
"eval_wer": 1.0228110922136269, |
|
"step": 75500 |
|
}, |
|
{ |
|
"epoch": 13.68, |
|
"eval_loss": 0.1727399230003357, |
|
"eval_runtime": 583.5966, |
|
"eval_samples_per_second": 25.855, |
|
"eval_steps_per_second": 3.233, |
|
"eval_wer": 1.0196777674146413, |
|
"step": 75600 |
|
}, |
|
{ |
|
"epoch": 13.69, |
|
"eval_loss": 0.17502325773239136, |
|
"eval_runtime": 764.0324, |
|
"eval_samples_per_second": 19.749, |
|
"eval_steps_per_second": 2.47, |
|
"eval_wer": 1.0252494772712033, |
|
"step": 75700 |
|
}, |
|
{ |
|
"epoch": 13.71, |
|
"eval_loss": 0.17015357315540314, |
|
"eval_runtime": 668.0971, |
|
"eval_samples_per_second": 22.585, |
|
"eval_steps_per_second": 2.824, |
|
"eval_wer": 1.0240729564809228, |
|
"step": 75800 |
|
}, |
|
{ |
|
"epoch": 13.73, |
|
"eval_loss": 0.17203068733215332, |
|
"eval_runtime": 590.9321, |
|
"eval_samples_per_second": 25.534, |
|
"eval_steps_per_second": 3.193, |
|
"eval_wer": 1.0249873508775138, |
|
"step": 75900 |
|
}, |
|
{ |
|
"epoch": 13.75, |
|
"learning_rate": 2.528997816064062e-05, |
|
"loss": 0.0433, |
|
"step": 76000 |
|
}, |
|
{ |
|
"epoch": 13.75, |
|
"eval_loss": 0.17436811327934265, |
|
"eval_runtime": 583.8521, |
|
"eval_samples_per_second": 25.844, |
|
"eval_steps_per_second": 3.232, |
|
"eval_wer": 1.0209823034204446, |
|
"step": 76000 |
|
}, |
|
{ |
|
"epoch": 13.77, |
|
"eval_loss": 0.17346572875976562, |
|
"eval_runtime": 751.961, |
|
"eval_samples_per_second": 20.066, |
|
"eval_steps_per_second": 2.509, |
|
"eval_wer": 1.0211164145986114, |
|
"step": 76100 |
|
}, |
|
{ |
|
"epoch": 13.78, |
|
"eval_loss": 0.17268899083137512, |
|
"eval_runtime": 698.8382, |
|
"eval_samples_per_second": 21.592, |
|
"eval_steps_per_second": 2.7, |
|
"eval_wer": 1.020537298147437, |
|
"step": 76200 |
|
}, |
|
{ |
|
"epoch": 13.8, |
|
"eval_loss": 0.17062433063983917, |
|
"eval_runtime": 597.277, |
|
"eval_samples_per_second": 25.263, |
|
"eval_steps_per_second": 3.159, |
|
"eval_wer": 1.0218174503026645, |
|
"step": 76300 |
|
}, |
|
{ |
|
"epoch": 13.82, |
|
"eval_loss": 0.17094029486179352, |
|
"eval_runtime": 582.5296, |
|
"eval_samples_per_second": 25.903, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.0237681583487257, |
|
"step": 76400 |
|
}, |
|
{ |
|
"epoch": 13.84, |
|
"learning_rate": 2.347003154574132e-05, |
|
"loss": 0.0431, |
|
"step": 76500 |
|
}, |
|
{ |
|
"epoch": 13.84, |
|
"eval_loss": 0.17047877609729767, |
|
"eval_runtime": 1185.1824, |
|
"eval_samples_per_second": 12.731, |
|
"eval_steps_per_second": 1.592, |
|
"eval_wer": 1.0196716714519973, |
|
"step": 76500 |
|
}, |
|
{ |
|
"epoch": 13.86, |
|
"eval_loss": 0.1734394133090973, |
|
"eval_runtime": 607.5712, |
|
"eval_samples_per_second": 24.835, |
|
"eval_steps_per_second": 3.106, |
|
"eval_wer": 1.0222929353888919, |
|
"step": 76600 |
|
}, |
|
{ |
|
"epoch": 13.87, |
|
"eval_loss": 0.1695163995027542, |
|
"eval_runtime": 597.2652, |
|
"eval_samples_per_second": 25.263, |
|
"eval_steps_per_second": 3.159, |
|
"eval_wer": 1.024969062989582, |
|
"step": 76700 |
|
}, |
|
{ |
|
"epoch": 13.89, |
|
"eval_loss": 0.17340916395187378, |
|
"eval_runtime": 583.1636, |
|
"eval_samples_per_second": 25.874, |
|
"eval_steps_per_second": 3.236, |
|
"eval_wer": 1.0231524661216875, |
|
"step": 76800 |
|
}, |
|
{ |
|
"epoch": 13.91, |
|
"eval_loss": 0.17240017652511597, |
|
"eval_runtime": 675.155, |
|
"eval_samples_per_second": 22.349, |
|
"eval_steps_per_second": 2.795, |
|
"eval_wer": 1.0219454655181872, |
|
"step": 76900 |
|
}, |
|
{ |
|
"epoch": 13.93, |
|
"learning_rate": 2.1653724824071823e-05, |
|
"loss": 0.041, |
|
"step": 77000 |
|
}, |
|
{ |
|
"epoch": 13.93, |
|
"eval_loss": 0.17061379551887512, |
|
"eval_runtime": 661.5346, |
|
"eval_samples_per_second": 22.809, |
|
"eval_steps_per_second": 2.852, |
|
"eval_wer": 1.0236035673573392, |
|
"step": 77000 |
|
}, |
|
{ |
|
"epoch": 13.95, |
|
"eval_loss": 0.1688837707042694, |
|
"eval_runtime": 591.3973, |
|
"eval_samples_per_second": 25.514, |
|
"eval_steps_per_second": 3.191, |
|
"eval_wer": 1.0220430009204904, |
|
"step": 77100 |
|
}, |
|
{ |
|
"epoch": 13.97, |
|
"eval_loss": 0.17377950251102448, |
|
"eval_runtime": 578.3142, |
|
"eval_samples_per_second": 26.091, |
|
"eval_steps_per_second": 3.263, |
|
"eval_wer": 1.0229939710929452, |
|
"step": 77200 |
|
}, |
|
{ |
|
"epoch": 13.98, |
|
"eval_loss": 0.17272156476974487, |
|
"eval_runtime": 885.5429, |
|
"eval_samples_per_second": 17.039, |
|
"eval_steps_per_second": 2.131, |
|
"eval_wer": 1.0253653005614383, |
|
"step": 77300 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_loss": 0.17211805284023285, |
|
"eval_runtime": 766.7304, |
|
"eval_samples_per_second": 19.68, |
|
"eval_steps_per_second": 2.461, |
|
"eval_wer": 1.026109008003999, |
|
"step": 77400 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 1.983377820917253e-05, |
|
"loss": 0.041, |
|
"step": 77500 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"eval_loss": 0.1759880930185318, |
|
"eval_runtime": 597.2455, |
|
"eval_samples_per_second": 25.264, |
|
"eval_steps_per_second": 3.16, |
|
"eval_wer": 1.0261394878172188, |
|
"step": 77500 |
|
}, |
|
{ |
|
"epoch": 14.04, |
|
"eval_loss": 0.17724254727363586, |
|
"eval_runtime": 582.654, |
|
"eval_samples_per_second": 25.897, |
|
"eval_steps_per_second": 3.239, |
|
"eval_wer": 1.020226404052596, |
|
"step": 77600 |
|
}, |
|
{ |
|
"epoch": 14.06, |
|
"eval_loss": 0.1781727820634842, |
|
"eval_runtime": 692.1827, |
|
"eval_samples_per_second": 21.799, |
|
"eval_steps_per_second": 2.726, |
|
"eval_wer": 1.02020202020202, |
|
"step": 77700 |
|
}, |
|
{ |
|
"epoch": 14.07, |
|
"eval_loss": 0.17770732939243317, |
|
"eval_runtime": 745.6874, |
|
"eval_samples_per_second": 20.235, |
|
"eval_steps_per_second": 2.531, |
|
"eval_wer": 1.0221527282480813, |
|
"step": 77800 |
|
}, |
|
{ |
|
"epoch": 14.09, |
|
"eval_loss": 0.17872411012649536, |
|
"eval_runtime": 597.5444, |
|
"eval_samples_per_second": 25.252, |
|
"eval_steps_per_second": 3.158, |
|
"eval_wer": 1.0202812677163915, |
|
"step": 77900 |
|
}, |
|
{ |
|
"epoch": 14.11, |
|
"learning_rate": 1.8013831594273232e-05, |
|
"loss": 0.0383, |
|
"step": 78000 |
|
}, |
|
{ |
|
"epoch": 14.11, |
|
"eval_loss": 0.17896606028079987, |
|
"eval_runtime": 582.3356, |
|
"eval_samples_per_second": 25.911, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.023634047170559, |
|
"step": 78000 |
|
}, |
|
{ |
|
"epoch": 14.13, |
|
"eval_loss": 0.18120603263378143, |
|
"eval_runtime": 1029.6119, |
|
"eval_samples_per_second": 14.655, |
|
"eval_steps_per_second": 1.833, |
|
"eval_wer": 1.0244691940527788, |
|
"step": 78100 |
|
}, |
|
{ |
|
"epoch": 14.15, |
|
"eval_loss": 0.17780369520187378, |
|
"eval_runtime": 616.7541, |
|
"eval_samples_per_second": 24.465, |
|
"eval_steps_per_second": 3.06, |
|
"eval_wer": 1.0223721829032633, |
|
"step": 78200 |
|
}, |
|
{ |
|
"epoch": 14.16, |
|
"eval_loss": 0.17714247107505798, |
|
"eval_runtime": 582.3156, |
|
"eval_samples_per_second": 25.912, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0230610266820286, |
|
"step": 78300 |
|
}, |
|
{ |
|
"epoch": 14.18, |
|
"eval_loss": 0.17816708981990814, |
|
"eval_runtime": 594.1683, |
|
"eval_samples_per_second": 25.395, |
|
"eval_steps_per_second": 3.176, |
|
"eval_wer": 1.0241765878458697, |
|
"step": 78400 |
|
}, |
|
{ |
|
"epoch": 14.2, |
|
"learning_rate": 1.6193884979373938e-05, |
|
"loss": 0.0391, |
|
"step": 78500 |
|
}, |
|
{ |
|
"epoch": 14.2, |
|
"eval_loss": 0.17851784825325012, |
|
"eval_runtime": 671.7395, |
|
"eval_samples_per_second": 22.463, |
|
"eval_steps_per_second": 2.809, |
|
"eval_wer": 1.026206543406302, |
|
"step": 78500 |
|
}, |
|
{ |
|
"epoch": 14.22, |
|
"eval_loss": 0.17911860346794128, |
|
"eval_runtime": 683.1816, |
|
"eval_samples_per_second": 22.086, |
|
"eval_steps_per_second": 2.762, |
|
"eval_wer": 1.0261211999292867, |
|
"step": 78600 |
|
}, |
|
{ |
|
"epoch": 14.24, |
|
"eval_loss": 0.1769927740097046, |
|
"eval_runtime": 582.2029, |
|
"eval_samples_per_second": 25.917, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0253592045987943, |
|
"step": 78700 |
|
}, |
|
{ |
|
"epoch": 14.25, |
|
"eval_loss": 0.1810205727815628, |
|
"eval_runtime": 581.863, |
|
"eval_samples_per_second": 25.932, |
|
"eval_steps_per_second": 3.243, |
|
"eval_wer": 1.025706674469499, |
|
"step": 78800 |
|
}, |
|
{ |
|
"epoch": 14.27, |
|
"eval_loss": 0.17939230799674988, |
|
"eval_runtime": 1170.3051, |
|
"eval_samples_per_second": 12.893, |
|
"eval_steps_per_second": 1.612, |
|
"eval_wer": 1.0240668605182788, |
|
"step": 78900 |
|
}, |
|
{ |
|
"epoch": 14.29, |
|
"learning_rate": 1.437393836447464e-05, |
|
"loss": 0.0387, |
|
"step": 79000 |
|
}, |
|
{ |
|
"epoch": 14.29, |
|
"eval_loss": 0.1773802638053894, |
|
"eval_runtime": 591.6412, |
|
"eval_samples_per_second": 25.504, |
|
"eval_steps_per_second": 3.189, |
|
"eval_wer": 1.0255542754034004, |
|
"step": 79000 |
|
}, |
|
{ |
|
"epoch": 14.31, |
|
"eval_loss": 0.17738394439220428, |
|
"eval_runtime": 592.5471, |
|
"eval_samples_per_second": 25.465, |
|
"eval_steps_per_second": 3.185, |
|
"eval_wer": 1.0236462390958467, |
|
"step": 79100 |
|
}, |
|
{ |
|
"epoch": 14.33, |
|
"eval_loss": 0.17587357759475708, |
|
"eval_runtime": 591.8296, |
|
"eval_samples_per_second": 25.496, |
|
"eval_steps_per_second": 3.188, |
|
"eval_wer": 1.0221710161360131, |
|
"step": 79200 |
|
}, |
|
{ |
|
"epoch": 14.35, |
|
"eval_loss": 0.178709477186203, |
|
"eval_runtime": 645.1624, |
|
"eval_samples_per_second": 23.388, |
|
"eval_steps_per_second": 2.925, |
|
"eval_wer": 1.023749870460794, |
|
"step": 79300 |
|
}, |
|
{ |
|
"epoch": 14.36, |
|
"eval_loss": 0.17875047028064728, |
|
"eval_runtime": 650.6934, |
|
"eval_samples_per_second": 23.189, |
|
"eval_steps_per_second": 2.9, |
|
"eval_wer": 1.0226525971848845, |
|
"step": 79400 |
|
}, |
|
{ |
|
"epoch": 14.38, |
|
"learning_rate": 1.2553991749575345e-05, |
|
"loss": 0.0372, |
|
"step": 79500 |
|
}, |
|
{ |
|
"epoch": 14.38, |
|
"eval_loss": 0.1789141446352005, |
|
"eval_runtime": 582.3073, |
|
"eval_samples_per_second": 25.912, |
|
"eval_steps_per_second": 3.241, |
|
"eval_wer": 1.0232073297854831, |
|
"step": 79500 |
|
}, |
|
{ |
|
"epoch": 14.4, |
|
"eval_loss": 0.17705988883972168, |
|
"eval_runtime": 581.24, |
|
"eval_samples_per_second": 25.96, |
|
"eval_steps_per_second": 3.247, |
|
"eval_wer": 1.0254201642252336, |
|
"step": 79600 |
|
}, |
|
{ |
|
"epoch": 14.42, |
|
"eval_loss": 0.17766208946704865, |
|
"eval_runtime": 833.161, |
|
"eval_samples_per_second": 18.111, |
|
"eval_steps_per_second": 2.265, |
|
"eval_wer": 1.0243655626878319, |
|
"step": 79700 |
|
}, |
|
{ |
|
"epoch": 14.44, |
|
"eval_loss": 0.17914512753486633, |
|
"eval_runtime": 650.6571, |
|
"eval_samples_per_second": 23.19, |
|
"eval_steps_per_second": 2.9, |
|
"eval_wer": 1.0224575263802784, |
|
"step": 79800 |
|
}, |
|
{ |
|
"epoch": 14.45, |
|
"eval_loss": 0.17859181761741638, |
|
"eval_runtime": 584.4617, |
|
"eval_samples_per_second": 25.817, |
|
"eval_steps_per_second": 3.229, |
|
"eval_wer": 1.0236584310211347, |
|
"step": 79900 |
|
}, |
|
{ |
|
"epoch": 14.47, |
|
"learning_rate": 1.0734045134676047e-05, |
|
"loss": 0.0385, |
|
"step": 80000 |
|
}, |
|
{ |
|
"epoch": 14.47, |
|
"eval_loss": 0.17818927764892578, |
|
"eval_runtime": 582.4141, |
|
"eval_samples_per_second": 25.908, |
|
"eval_steps_per_second": 3.24, |
|
"eval_wer": 1.0243106990240365, |
|
"step": 80000 |
|
}, |
|
{ |
|
"epoch": 14.49, |
|
"eval_loss": 0.17697465419769287, |
|
"eval_runtime": 823.197, |
|
"eval_samples_per_second": 18.33, |
|
"eval_steps_per_second": 2.292, |
|
"eval_wer": 1.0235608956188316, |
|
"step": 80100 |
|
}, |
|
{ |
|
"epoch": 14.51, |
|
"eval_loss": 0.17824648320674896, |
|
"eval_runtime": 744.1916, |
|
"eval_samples_per_second": 20.276, |
|
"eval_steps_per_second": 2.536, |
|
"eval_wer": 1.024048572630347, |
|
"step": 80200 |
|
}, |
|
{ |
|
"epoch": 14.53, |
|
"eval_loss": 0.17638903856277466, |
|
"eval_runtime": 648.9894, |
|
"eval_samples_per_second": 23.25, |
|
"eval_steps_per_second": 2.908, |
|
"eval_wer": 1.0242924111361045, |
|
"step": 80300 |
|
}, |
|
{ |
|
"epoch": 14.54, |
|
"eval_loss": 0.17475561797618866, |
|
"eval_runtime": 598.8711, |
|
"eval_samples_per_second": 25.196, |
|
"eval_steps_per_second": 3.151, |
|
"eval_wer": 1.0247922800729077, |
|
"step": 80400 |
|
}, |
|
{ |
|
"epoch": 14.56, |
|
"learning_rate": 8.914098519776751e-06, |
|
"loss": 0.039, |
|
"step": 80500 |
|
}, |
|
{ |
|
"epoch": 14.56, |
|
"eval_loss": 0.17579643428325653, |
|
"eval_runtime": 581.6292, |
|
"eval_samples_per_second": 25.943, |
|
"eval_steps_per_second": 3.244, |
|
"eval_wer": 1.0231768499722633, |
|
"step": 80500 |
|
}, |
|
{ |
|
"epoch": 14.58, |
|
"eval_loss": 0.17633995413780212, |
|
"eval_runtime": 582.92, |
|
"eval_samples_per_second": 25.885, |
|
"eval_steps_per_second": 3.237, |
|
"eval_wer": 1.024554537529794, |
|
"step": 80600 |
|
}, |
|
{ |
|
"epoch": 14.6, |
|
"eval_loss": 0.17696543037891388, |
|
"eval_runtime": 601.3023, |
|
"eval_samples_per_second": 25.094, |
|
"eval_steps_per_second": 3.138, |
|
"eval_wer": 1.0219637534061192, |
|
"step": 80700 |
|
}, |
|
{ |
|
"epoch": 14.62, |
|
"eval_loss": 0.1788012832403183, |
|
"eval_runtime": 593.5049, |
|
"eval_samples_per_second": 25.424, |
|
"eval_steps_per_second": 3.179, |
|
"eval_wer": 1.0225123900440738, |
|
"step": 80800 |
|
}, |
|
{ |
|
"epoch": 14.63, |
|
"eval_loss": 0.178111732006073, |
|
"eval_runtime": 660.5078, |
|
"eval_samples_per_second": 22.845, |
|
"eval_steps_per_second": 2.857, |
|
"eval_wer": 1.0229817791676572, |
|
"step": 80900 |
|
}, |
|
{ |
|
"epoch": 14.65, |
|
"learning_rate": 7.0941519048774565e-06, |
|
"loss": 0.039, |
|
"step": 81000 |
|
}, |
|
{ |
|
"epoch": 14.65, |
|
"eval_loss": 0.1779184192419052, |
|
"eval_runtime": 664.0205, |
|
"eval_samples_per_second": 22.724, |
|
"eval_steps_per_second": 2.842, |
|
"eval_wer": 1.0229634912797254, |
|
"step": 81000 |
|
}, |
|
{ |
|
"epoch": 14.67, |
|
"eval_loss": 0.17550311982631683, |
|
"eval_runtime": 596.9003, |
|
"eval_samples_per_second": 25.279, |
|
"eval_steps_per_second": 3.161, |
|
"eval_wer": 1.0212261419262023, |
|
"step": 81100 |
|
}, |
|
{ |
|
"epoch": 14.69, |
|
"eval_loss": 0.17648081481456757, |
|
"eval_runtime": 601.4761, |
|
"eval_samples_per_second": 25.087, |
|
"eval_steps_per_second": 3.137, |
|
"eval_wer": 1.0226221173716648, |
|
"step": 81200 |
|
}, |
|
{ |
|
"epoch": 14.71, |
|
"eval_loss": 0.17868663370609283, |
|
"eval_runtime": 993.2238, |
|
"eval_samples_per_second": 15.192, |
|
"eval_steps_per_second": 1.9, |
|
"eval_wer": 1.0241095322567864, |
|
"step": 81300 |
|
}, |
|
{ |
|
"epoch": 14.72, |
|
"eval_loss": 0.17815029621124268, |
|
"eval_runtime": 781.2891, |
|
"eval_samples_per_second": 19.313, |
|
"eval_steps_per_second": 2.415, |
|
"eval_wer": 1.0249507751016502, |
|
"step": 81400 |
|
}, |
|
{ |
|
"epoch": 14.74, |
|
"learning_rate": 5.274205289978161e-06, |
|
"loss": 0.0368, |
|
"step": 81500 |
|
}, |
|
{ |
|
"epoch": 14.74, |
|
"eval_loss": 0.1779765784740448, |
|
"eval_runtime": 580.5095, |
|
"eval_samples_per_second": 25.993, |
|
"eval_steps_per_second": 3.251, |
|
"eval_wer": 1.0248471437367033, |
|
"step": 81500 |
|
}, |
|
{ |
|
"epoch": 14.76, |
|
"eval_loss": 0.17816530168056488, |
|
"eval_runtime": 580.9073, |
|
"eval_samples_per_second": 25.975, |
|
"eval_steps_per_second": 3.248, |
|
"eval_wer": 1.0242009716964455, |
|
"step": 81600 |
|
}, |
|
{ |
|
"epoch": 14.78, |
|
"eval_loss": 0.17820771038532257, |
|
"eval_runtime": 616.5224, |
|
"eval_samples_per_second": 24.474, |
|
"eval_steps_per_second": 3.061, |
|
"eval_wer": 1.0241948757338015, |
|
"step": 81700 |
|
}, |
|
{ |
|
"epoch": 14.8, |
|
"eval_loss": 0.17921525239944458, |
|
"eval_runtime": 743.3365, |
|
"eval_samples_per_second": 20.299, |
|
"eval_steps_per_second": 2.539, |
|
"eval_wer": 1.0240607645556348, |
|
"step": 81800 |
|
}, |
|
{ |
|
"epoch": 14.82, |
|
"eval_loss": 0.17964446544647217, |
|
"eval_runtime": 601.8651, |
|
"eval_samples_per_second": 25.07, |
|
"eval_steps_per_second": 3.135, |
|
"eval_wer": 1.0237864462366575, |
|
"step": 81900 |
|
}, |
|
{ |
|
"epoch": 14.83, |
|
"learning_rate": 3.454258675078864e-06, |
|
"loss": 0.0378, |
|
"step": 82000 |
|
}, |
|
{ |
|
"epoch": 14.83, |
|
"eval_loss": 0.179461270570755, |
|
"eval_runtime": 589.9434, |
|
"eval_samples_per_second": 25.577, |
|
"eval_steps_per_second": 3.199, |
|
"eval_wer": 1.0235852794694074, |
|
"step": 82000 |
|
}, |
|
{ |
|
"epoch": 14.85, |
|
"eval_loss": 0.17961536347866058, |
|
"eval_runtime": 789.7316, |
|
"eval_samples_per_second": 19.106, |
|
"eval_steps_per_second": 2.389, |
|
"eval_wer": 1.0238595977883846, |
|
"step": 82100 |
|
}, |
|
{ |
|
"epoch": 14.87, |
|
"eval_loss": 0.17919617891311646, |
|
"eval_runtime": 675.851, |
|
"eval_samples_per_second": 22.326, |
|
"eval_steps_per_second": 2.792, |
|
"eval_wer": 1.023627951207915, |
|
"step": 82200 |
|
}, |
|
{ |
|
"epoch": 14.89, |
|
"eval_loss": 0.17886628210544586, |
|
"eval_runtime": 587.1989, |
|
"eval_samples_per_second": 25.697, |
|
"eval_steps_per_second": 3.214, |
|
"eval_wer": 1.0239205574148242, |
|
"step": 82300 |
|
}, |
|
{ |
|
"epoch": 14.91, |
|
"eval_loss": 0.17884646356105804, |
|
"eval_runtime": 588.7054, |
|
"eval_samples_per_second": 25.631, |
|
"eval_steps_per_second": 3.205, |
|
"eval_wer": 1.0237559664234377, |
|
"step": 82400 |
|
}, |
|
{ |
|
"epoch": 14.92, |
|
"learning_rate": 1.6379519534093665e-06, |
|
"loss": 0.0386, |
|
"step": 82500 |
|
}, |
|
{ |
|
"epoch": 14.92, |
|
"eval_loss": 0.1787010282278061, |
|
"eval_runtime": 856.6484, |
|
"eval_samples_per_second": 17.614, |
|
"eval_steps_per_second": 2.203, |
|
"eval_wer": 1.023926653377468, |
|
"step": 82500 |
|
}, |
|
{ |
|
"epoch": 14.94, |
|
"eval_loss": 0.178622305393219, |
|
"eval_runtime": 701.0154, |
|
"eval_samples_per_second": 21.524, |
|
"eval_steps_per_second": 2.692, |
|
"eval_wer": 1.0236096633199832, |
|
"step": 82600 |
|
}, |
|
{ |
|
"epoch": 14.96, |
|
"eval_loss": 0.17859022319316864, |
|
"eval_runtime": 596.8373, |
|
"eval_samples_per_second": 25.282, |
|
"eval_steps_per_second": 3.162, |
|
"eval_wer": 1.023749870460794, |
|
"step": 82700 |
|
}, |
|
{ |
|
"epoch": 14.98, |
|
"eval_loss": 0.17872443795204163, |
|
"eval_runtime": 582.8487, |
|
"eval_samples_per_second": 25.888, |
|
"eval_steps_per_second": 3.238, |
|
"eval_wer": 1.0239449412654, |
|
"step": 82800 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"eval_loss": 0.17875000834465027, |
|
"eval_runtime": 977.9873, |
|
"eval_samples_per_second": 15.429, |
|
"eval_steps_per_second": 1.929, |
|
"eval_wer": 1.0237925421993015, |
|
"step": 82900 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"step": 82920, |
|
"total_flos": 4.324450877447923e+20, |
|
"train_loss": 0.14314281111228197, |
|
"train_runtime": 767473.646, |
|
"train_samples_per_second": 3.457, |
|
"train_steps_per_second": 0.108 |
|
} |
|
], |
|
"max_steps": 82920, |
|
"num_train_epochs": 15, |
|
"total_flos": 4.324450877447923e+20, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|