| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.99892202659001, | |
| "global_step": 34750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.6e-06, | |
| "loss": 27.8845, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.35e-06, | |
| "loss": 5.2607, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1099999999999999e-05, | |
| "loss": 4.8397, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.485e-05, | |
| "loss": 4.6751, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8599999999999998e-05, | |
| "loss": 4.603, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 4.657182693481445, | |
| "eval_runtime": 61.7478, | |
| "eval_samples_per_second": 7.385, | |
| "eval_steps_per_second": 0.923, | |
| "eval_wer": 0.9984898822108125, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.2349999999999998e-05, | |
| "loss": 4.5246, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.6099999999999997e-05, | |
| "loss": 3.8527, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.985e-05, | |
| "loss": 3.0344, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.36e-05, | |
| "loss": 2.7616, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.735e-05, | |
| "loss": 2.6314, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 2.0424230098724365, | |
| "eval_runtime": 57.8725, | |
| "eval_samples_per_second": 7.879, | |
| "eval_steps_per_second": 0.985, | |
| "eval_wer": 0.9255511929930534, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.11e-05, | |
| "loss": 2.4936, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.484999999999999e-05, | |
| "loss": 2.4557, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.8599999999999995e-05, | |
| "loss": 2.3667, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.234999999999999e-05, | |
| "loss": 2.3147, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.6099999999999995e-05, | |
| "loss": 2.2708, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.9889274835586548, | |
| "eval_runtime": 59.1503, | |
| "eval_samples_per_second": 7.709, | |
| "eval_steps_per_second": 0.964, | |
| "eval_wer": 0.6988825128360012, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 5.985e-05, | |
| "loss": 2.1797, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 6.359999999999999e-05, | |
| "loss": 2.1628, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.735e-05, | |
| "loss": 2.1662, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.11e-05, | |
| "loss": 2.1623, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.484999999999999e-05, | |
| "loss": 2.1769, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.8366215825080872, | |
| "eval_runtime": 56.673, | |
| "eval_samples_per_second": 8.046, | |
| "eval_steps_per_second": 1.006, | |
| "eval_wer": 0.6312292358803987, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.478015267175572e-05, | |
| "loss": 2.1913, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.455114503816793e-05, | |
| "loss": 2.1906, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 7.432213740458014e-05, | |
| "loss": 2.1964, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 7.409312977099236e-05, | |
| "loss": 2.1548, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 7.386412213740458e-05, | |
| "loss": 2.1142, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.7555108070373535, | |
| "eval_runtime": 57.6601, | |
| "eval_samples_per_second": 7.908, | |
| "eval_steps_per_second": 0.989, | |
| "eval_wer": 0.5998187858652975, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.363511450381678e-05, | |
| "loss": 2.1028, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 7.3406106870229e-05, | |
| "loss": 2.0524, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.317709923664121e-05, | |
| "loss": 2.0426, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 7.29503816793893e-05, | |
| "loss": 1.9613, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.272137404580152e-05, | |
| "loss": 2.0084, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "eval_loss": 0.7143925428390503, | |
| "eval_runtime": 57.4263, | |
| "eval_samples_per_second": 7.941, | |
| "eval_steps_per_second": 0.993, | |
| "eval_wer": 0.6002718212020538, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 7.249236641221373e-05, | |
| "loss": 2.0063, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 7.226335877862594e-05, | |
| "loss": 1.9758, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 7.203435114503816e-05, | |
| "loss": 1.9313, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 7.180534351145037e-05, | |
| "loss": 1.9009, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 7.15763358778626e-05, | |
| "loss": 1.9272, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "eval_loss": 0.631069004535675, | |
| "eval_runtime": 58.3633, | |
| "eval_samples_per_second": 7.813, | |
| "eval_steps_per_second": 0.977, | |
| "eval_wer": 0.5460585925702205, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 7.13473282442748e-05, | |
| "loss": 1.8728, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 7.111832061068701e-05, | |
| "loss": 1.8675, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 7.088931297709923e-05, | |
| "loss": 1.8549, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 7.066030534351145e-05, | |
| "loss": 1.8491, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 7.043358778625953e-05, | |
| "loss": 1.8687, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_loss": 0.6252322196960449, | |
| "eval_runtime": 56.9578, | |
| "eval_samples_per_second": 8.006, | |
| "eval_steps_per_second": 1.001, | |
| "eval_wer": 0.5430383569918453, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 7.020458015267175e-05, | |
| "loss": 1.8377, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 6.997557251908396e-05, | |
| "loss": 1.8436, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 6.974656488549617e-05, | |
| "loss": 1.7895, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 6.951755725190839e-05, | |
| "loss": 1.8045, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 6.928854961832061e-05, | |
| "loss": 1.8186, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 0.5491229891777039, | |
| "eval_runtime": 56.8943, | |
| "eval_samples_per_second": 8.015, | |
| "eval_steps_per_second": 1.002, | |
| "eval_wer": 0.49879190576864996, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 6.905954198473281e-05, | |
| "loss": 1.79, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 6.883053435114503e-05, | |
| "loss": 1.8018, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 6.860152671755724e-05, | |
| "loss": 1.7966, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 6.837251908396947e-05, | |
| "loss": 1.7979, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 6.814351145038167e-05, | |
| "loss": 1.7364, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "eval_loss": 0.5463064908981323, | |
| "eval_runtime": 56.8201, | |
| "eval_samples_per_second": 8.025, | |
| "eval_steps_per_second": 1.003, | |
| "eval_wer": 0.4959226819691936, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 6.791450381679388e-05, | |
| "loss": 1.7467, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 6.76854961832061e-05, | |
| "loss": 1.7082, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 6.745648854961832e-05, | |
| "loss": 1.7084, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 6.72297709923664e-05, | |
| "loss": 1.6732, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 6.700076335877863e-05, | |
| "loss": 1.6809, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_loss": 0.47242555022239685, | |
| "eval_runtime": 56.3595, | |
| "eval_samples_per_second": 8.091, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.4483539716097856, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 6.677175572519083e-05, | |
| "loss": 1.7139, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 6.654274809160304e-05, | |
| "loss": 1.708, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 6.631374045801526e-05, | |
| "loss": 1.6987, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 6.608473282442748e-05, | |
| "loss": 1.6705, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 6.585572519083968e-05, | |
| "loss": 1.641, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "eval_loss": 0.46793004870414734, | |
| "eval_runtime": 56.3201, | |
| "eval_samples_per_second": 8.097, | |
| "eval_steps_per_second": 1.012, | |
| "eval_wer": 0.44608879492600423, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 6.56267175572519e-05, | |
| "loss": 1.6277, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 6.539770992366411e-05, | |
| "loss": 1.6529, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 6.516870229007634e-05, | |
| "loss": 1.6195, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 6.493969465648855e-05, | |
| "loss": 1.5983, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 6.471068702290075e-05, | |
| "loss": 1.572, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "eval_loss": 0.4386586844921112, | |
| "eval_runtime": 56.3246, | |
| "eval_samples_per_second": 8.096, | |
| "eval_steps_per_second": 1.012, | |
| "eval_wer": 0.42358803986710963, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 6.448167938931296e-05, | |
| "loss": 1.5749, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 6.425267175572519e-05, | |
| "loss": 1.5561, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 6.40236641221374e-05, | |
| "loss": 1.559, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 6.379465648854962e-05, | |
| "loss": 1.5419, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 6.356564885496182e-05, | |
| "loss": 1.5256, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "eval_loss": 0.39700397849082947, | |
| "eval_runtime": 57.819, | |
| "eval_samples_per_second": 7.887, | |
| "eval_steps_per_second": 0.986, | |
| "eval_wer": 0.4003322259136213, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 6.333664122137404e-05, | |
| "loss": 1.5122, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 6.310763358778626e-05, | |
| "loss": 1.4812, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 6.287862595419847e-05, | |
| "loss": 1.4997, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 6.264961832061068e-05, | |
| "loss": 1.4933, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 6.24206106870229e-05, | |
| "loss": 1.5044, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "eval_loss": 0.3689935803413391, | |
| "eval_runtime": 56.6639, | |
| "eval_samples_per_second": 8.047, | |
| "eval_steps_per_second": 1.006, | |
| "eval_wer": 0.3893083660525521, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 6.219160305343511e-05, | |
| "loss": 1.475, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 6.196259541984733e-05, | |
| "loss": 1.4826, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 6.173358778625954e-05, | |
| "loss": 1.4336, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 6.150458015267175e-05, | |
| "loss": 1.4338, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 6.127557251908397e-05, | |
| "loss": 1.4563, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "eval_loss": 0.37522608041763306, | |
| "eval_runtime": 56.3933, | |
| "eval_samples_per_second": 8.086, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.387496224705527, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 6.104656488549618e-05, | |
| "loss": 1.45, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 6.0817557251908386e-05, | |
| "loss": 1.4476, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 6.0588549618320606e-05, | |
| "loss": 1.4255, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 6.035954198473282e-05, | |
| "loss": 1.4266, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 6.013053435114503e-05, | |
| "loss": 1.394, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "eval_loss": 0.3385707437992096, | |
| "eval_runtime": 56.4365, | |
| "eval_samples_per_second": 8.08, | |
| "eval_steps_per_second": 1.01, | |
| "eval_wer": 0.35668982180610087, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 5.9901526717557246e-05, | |
| "loss": 1.4002, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 5.9672519083969466e-05, | |
| "loss": 1.3823, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 5.944351145038167e-05, | |
| "loss": 1.3834, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 5.9214503816793886e-05, | |
| "loss": 1.3765, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 5.89854961832061e-05, | |
| "loss": 1.3641, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "eval_loss": 0.3289976716041565, | |
| "eval_runtime": 57.6648, | |
| "eval_samples_per_second": 7.908, | |
| "eval_steps_per_second": 0.988, | |
| "eval_wer": 0.346723044397463, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 5.875648854961832e-05, | |
| "loss": 1.3599, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 5.8527480916030534e-05, | |
| "loss": 1.3234, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 5.829847328244274e-05, | |
| "loss": 1.3323, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 5.8069465648854954e-05, | |
| "loss": 1.3002, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 5.7840458015267174e-05, | |
| "loss": 1.2878, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "eval_loss": 0.28934037685394287, | |
| "eval_runtime": 56.1939, | |
| "eval_samples_per_second": 8.115, | |
| "eval_steps_per_second": 1.014, | |
| "eval_wer": 0.31350045303533675, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 5.761145038167939e-05, | |
| "loss": 1.2958, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 5.73824427480916e-05, | |
| "loss": 1.293, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 5.715343511450381e-05, | |
| "loss": 1.286, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 5.692442748091603e-05, | |
| "loss": 1.2912, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "learning_rate": 5.669541984732824e-05, | |
| "loss": 1.2602, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "eval_loss": 0.2723310589790344, | |
| "eval_runtime": 57.7364, | |
| "eval_samples_per_second": 7.898, | |
| "eval_steps_per_second": 0.987, | |
| "eval_wer": 0.30292962851102384, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 5.6466412213740455e-05, | |
| "loss": 1.2386, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 5.623740458015266e-05, | |
| "loss": 1.247, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 5.600839694656488e-05, | |
| "loss": 1.2611, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 5.5779389312977095e-05, | |
| "loss": 1.2238, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 5.555038167938931e-05, | |
| "loss": 1.2302, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "eval_loss": 0.260337769985199, | |
| "eval_runtime": 56.8447, | |
| "eval_samples_per_second": 8.022, | |
| "eval_steps_per_second": 1.003, | |
| "eval_wer": 0.29885231048021743, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 5.532137404580152e-05, | |
| "loss": 1.2119, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 5.509236641221373e-05, | |
| "loss": 1.205, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 5.486335877862595e-05, | |
| "loss": 1.1929, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.463435114503816e-05, | |
| "loss": 1.1917, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 5.4405343511450376e-05, | |
| "loss": 1.1865, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "eval_loss": 0.24401792883872986, | |
| "eval_runtime": 56.3786, | |
| "eval_samples_per_second": 8.088, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.279371790999698, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 5.417633587786259e-05, | |
| "loss": 1.1634, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 5.394732824427481e-05, | |
| "loss": 1.162, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 5.3718320610687016e-05, | |
| "loss": 1.1556, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 5.348931297709923e-05, | |
| "loss": 1.1432, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 5.326030534351144e-05, | |
| "loss": 1.1491, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 0.24998041987419128, | |
| "eval_runtime": 57.3291, | |
| "eval_samples_per_second": 7.954, | |
| "eval_steps_per_second": 0.994, | |
| "eval_wer": 0.278767743884023, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 5.303129770992366e-05, | |
| "loss": 1.1351, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 5.280458015267176e-05, | |
| "loss": 1.1448, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "learning_rate": 5.2575572519083964e-05, | |
| "loss": 1.123, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 5.234656488549618e-05, | |
| "loss": 1.1066, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "learning_rate": 5.211755725190839e-05, | |
| "loss": 1.093, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "eval_loss": 0.22785192728042603, | |
| "eval_runtime": 57.123, | |
| "eval_samples_per_second": 7.983, | |
| "eval_steps_per_second": 0.998, | |
| "eval_wer": 0.2629115070975536, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 5.188854961832061e-05, | |
| "loss": 1.115, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 17.55, | |
| "learning_rate": 5.1659541984732825e-05, | |
| "loss": 1.0895, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 5.143053435114503e-05, | |
| "loss": 1.0705, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 5.1201526717557245e-05, | |
| "loss": 1.07, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "learning_rate": 5.0972519083969465e-05, | |
| "loss": 1.0367, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_loss": 0.2076062262058258, | |
| "eval_runtime": 56.1861, | |
| "eval_samples_per_second": 8.116, | |
| "eval_steps_per_second": 1.014, | |
| "eval_wer": 0.24433705829054667, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 5.074351145038168e-05, | |
| "loss": 1.0313, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 5.051450381679389e-05, | |
| "loss": 1.0236, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 18.42, | |
| "learning_rate": 5.02854961832061e-05, | |
| "loss": 1.0035, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 5.005648854961831e-05, | |
| "loss": 1.0105, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "learning_rate": 4.982748091603053e-05, | |
| "loss": 0.9954, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "eval_loss": 0.18436060845851898, | |
| "eval_runtime": 58.6813, | |
| "eval_samples_per_second": 7.771, | |
| "eval_steps_per_second": 0.971, | |
| "eval_wer": 0.22591362126245848, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 4.9598473282442746e-05, | |
| "loss": 0.9883, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 4.936946564885495e-05, | |
| "loss": 0.9908, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 4.9140458015267166e-05, | |
| "loss": 0.9634, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 19.28, | |
| "learning_rate": 4.8911450381679386e-05, | |
| "loss": 0.9628, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 4.86824427480916e-05, | |
| "loss": 0.99, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "eval_loss": 0.17937178909778595, | |
| "eval_runtime": 57.9354, | |
| "eval_samples_per_second": 7.871, | |
| "eval_steps_per_second": 0.984, | |
| "eval_wer": 0.21790999697976443, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 4.845343511450381e-05, | |
| "loss": 0.9627, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 4.822442748091602e-05, | |
| "loss": 0.969, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 4.799541984732824e-05, | |
| "loss": 0.9507, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.776641221374045e-05, | |
| "loss": 0.9696, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 4.753740458015267e-05, | |
| "loss": 0.9385, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "eval_loss": 0.1765013188123703, | |
| "eval_runtime": 56.2969, | |
| "eval_samples_per_second": 8.1, | |
| "eval_steps_per_second": 1.012, | |
| "eval_wer": 0.2121715493808517, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 20.29, | |
| "learning_rate": 4.730839694656488e-05, | |
| "loss": 0.9264, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 4.70793893129771e-05, | |
| "loss": 0.9399, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "learning_rate": 4.685038167938931e-05, | |
| "loss": 0.923, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 20.72, | |
| "learning_rate": 4.662137404580152e-05, | |
| "loss": 0.9128, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "learning_rate": 4.6392366412213734e-05, | |
| "loss": 0.8952, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_loss": 0.17056496441364288, | |
| "eval_runtime": 56.9013, | |
| "eval_samples_per_second": 8.014, | |
| "eval_steps_per_second": 1.002, | |
| "eval_wer": 0.19737239504681364, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 4.6163358778625954e-05, | |
| "loss": 0.9509, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 4.593435114503817e-05, | |
| "loss": 0.8967, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "learning_rate": 4.5705343511450374e-05, | |
| "loss": 0.8928, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 4.547633587786259e-05, | |
| "loss": 0.8731, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 21.58, | |
| "learning_rate": 4.524732824427481e-05, | |
| "loss": 0.8841, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 21.58, | |
| "eval_loss": 0.17911894619464874, | |
| "eval_runtime": 56.4012, | |
| "eval_samples_per_second": 8.085, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.1969193597100574, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 21.73, | |
| "learning_rate": 4.501832061068702e-05, | |
| "loss": 0.8816, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 4.4789312977099235e-05, | |
| "loss": 0.8801, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 4.456030534351144e-05, | |
| "loss": 0.9044, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 22.16, | |
| "learning_rate": 4.433129770992366e-05, | |
| "loss": 0.8849, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 22.3, | |
| "learning_rate": 4.4102290076335875e-05, | |
| "loss": 0.847, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 22.3, | |
| "eval_loss": 0.17799803614616394, | |
| "eval_runtime": 57.0716, | |
| "eval_samples_per_second": 7.99, | |
| "eval_steps_per_second": 0.999, | |
| "eval_wer": 0.2059800664451827, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "learning_rate": 4.387328244274809e-05, | |
| "loss": 0.8805, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 22.59, | |
| "learning_rate": 4.3644274809160295e-05, | |
| "loss": 0.8516, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "learning_rate": 4.341984732824427e-05, | |
| "loss": 0.8137, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 4.3190839694656484e-05, | |
| "loss": 0.8335, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 4.29618320610687e-05, | |
| "loss": 0.8669, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_loss": 0.16084039211273193, | |
| "eval_runtime": 58.1201, | |
| "eval_samples_per_second": 7.846, | |
| "eval_steps_per_second": 0.981, | |
| "eval_wer": 0.18619752340682574, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "learning_rate": 4.273282442748092e-05, | |
| "loss": 0.8242, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 23.31, | |
| "learning_rate": 4.250381679389313e-05, | |
| "loss": 0.8384, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 4.227480916030534e-05, | |
| "loss": 0.8376, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 4.204809160305343e-05, | |
| "loss": 0.8277, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "learning_rate": 4.1819083969465645e-05, | |
| "loss": 0.8066, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "eval_loss": 0.14472883939743042, | |
| "eval_runtime": 58.2049, | |
| "eval_samples_per_second": 7.834, | |
| "eval_steps_per_second": 0.979, | |
| "eval_wer": 0.16263968589549985, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 4.159007633587786e-05, | |
| "loss": 0.8056, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 4.136106870229008e-05, | |
| "loss": 0.8128, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 4.1132061068702285e-05, | |
| "loss": 0.8095, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 4.09030534351145e-05, | |
| "loss": 0.7816, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 24.46, | |
| "learning_rate": 4.067404580152671e-05, | |
| "loss": 0.7908, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 24.46, | |
| "eval_loss": 0.14570841193199158, | |
| "eval_runtime": 56.8345, | |
| "eval_samples_per_second": 8.023, | |
| "eval_steps_per_second": 1.003, | |
| "eval_wer": 0.1655089096949562, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "learning_rate": 4.044503816793893e-05, | |
| "loss": 0.7846, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 4.0216030534351146e-05, | |
| "loss": 0.7735, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 3.998702290076335e-05, | |
| "loss": 0.772, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 3.9758015267175566e-05, | |
| "loss": 0.7676, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 3.9529007633587786e-05, | |
| "loss": 0.7459, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "eval_loss": 0.13501976430416107, | |
| "eval_runtime": 56.9549, | |
| "eval_samples_per_second": 8.006, | |
| "eval_steps_per_second": 1.001, | |
| "eval_wer": 0.14451827242524917, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 3.93e-05, | |
| "loss": 0.7394, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 25.47, | |
| "learning_rate": 3.9070992366412206e-05, | |
| "loss": 0.727, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 25.61, | |
| "learning_rate": 3.884198473282442e-05, | |
| "loss": 0.7255, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 3.861297709923664e-05, | |
| "loss": 0.7122, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "learning_rate": 3.8383969465648854e-05, | |
| "loss": 0.7218, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "eval_loss": 0.12762019038200378, | |
| "eval_runtime": 56.702, | |
| "eval_samples_per_second": 8.042, | |
| "eval_steps_per_second": 1.005, | |
| "eval_wer": 0.1421020839625491, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 26.04, | |
| "learning_rate": 3.815496183206107e-05, | |
| "loss": 0.7219, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 26.19, | |
| "learning_rate": 3.7925954198473274e-05, | |
| "loss": 0.6954, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 26.33, | |
| "learning_rate": 3.7696946564885494e-05, | |
| "loss": 0.6874, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 26.47, | |
| "learning_rate": 3.746793893129771e-05, | |
| "loss": 0.6974, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 26.62, | |
| "learning_rate": 3.7241221374045795e-05, | |
| "loss": 0.703, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 26.62, | |
| "eval_loss": 0.11774259060621262, | |
| "eval_runtime": 58.7528, | |
| "eval_samples_per_second": 7.761, | |
| "eval_steps_per_second": 0.97, | |
| "eval_wer": 0.13017215342796737, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 3.7012213740458015e-05, | |
| "loss": 0.6976, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 26.91, | |
| "learning_rate": 3.678320610687022e-05, | |
| "loss": 0.7008, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "learning_rate": 3.655419847328244e-05, | |
| "loss": 0.6815, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 27.19, | |
| "learning_rate": 3.6325190839694655e-05, | |
| "loss": 0.6783, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 27.34, | |
| "learning_rate": 3.609618320610687e-05, | |
| "loss": 0.685, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 27.34, | |
| "eval_loss": 0.11473936587572098, | |
| "eval_runtime": 56.5545, | |
| "eval_samples_per_second": 8.063, | |
| "eval_steps_per_second": 1.008, | |
| "eval_wer": 0.13047417698580488, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 27.48, | |
| "learning_rate": 3.586717557251908e-05, | |
| "loss": 0.6828, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 27.63, | |
| "learning_rate": 3.5638167938931296e-05, | |
| "loss": 0.6899, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 27.77, | |
| "learning_rate": 3.540916030534351e-05, | |
| "loss": 0.6889, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 3.518015267175572e-05, | |
| "loss": 0.689, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 3.4951145038167936e-05, | |
| "loss": 0.6811, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "eval_loss": 0.11280036717653275, | |
| "eval_runtime": 57.3287, | |
| "eval_samples_per_second": 7.954, | |
| "eval_steps_per_second": 0.994, | |
| "eval_wer": 0.12443370582905466, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "learning_rate": 3.472213740458015e-05, | |
| "loss": 0.6599, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "learning_rate": 3.449312977099236e-05, | |
| "loss": 0.655, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 28.49, | |
| "learning_rate": 3.4264122137404576e-05, | |
| "loss": 0.6577, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 28.63, | |
| "learning_rate": 3.403511450381679e-05, | |
| "loss": 0.6562, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 28.78, | |
| "learning_rate": 3.3806106870229e-05, | |
| "loss": 0.6444, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 28.78, | |
| "eval_loss": 0.11200590431690216, | |
| "eval_runtime": 56.8504, | |
| "eval_samples_per_second": 8.021, | |
| "eval_steps_per_second": 1.003, | |
| "eval_wer": 0.1212624584717608, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 3.357709923664122e-05, | |
| "loss": 0.6543, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 29.06, | |
| "learning_rate": 3.334809160305344e-05, | |
| "loss": 0.6337, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 29.21, | |
| "learning_rate": 3.3119083969465644e-05, | |
| "loss": 0.613, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 3.2890076335877864e-05, | |
| "loss": 0.6197, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 3.266106870229007e-05, | |
| "loss": 0.6323, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "eval_loss": 0.11374162137508392, | |
| "eval_runtime": 56.3556, | |
| "eval_samples_per_second": 8.091, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.11658109332527937, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 29.64, | |
| "learning_rate": 3.243206106870229e-05, | |
| "loss": 0.6182, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "learning_rate": 3.2203053435114504e-05, | |
| "loss": 0.6298, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 29.93, | |
| "learning_rate": 3.197404580152672e-05, | |
| "loss": 0.6143, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 30.07, | |
| "learning_rate": 3.174503816793893e-05, | |
| "loss": 0.5943, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 3.1516030534351145e-05, | |
| "loss": 0.5998, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "eval_loss": 0.10512539744377136, | |
| "eval_runtime": 56.712, | |
| "eval_samples_per_second": 8.041, | |
| "eval_steps_per_second": 1.005, | |
| "eval_wer": 0.1106916339474479, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 3.128702290076336e-05, | |
| "loss": 0.6093, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 30.5, | |
| "learning_rate": 3.1058015267175565e-05, | |
| "loss": 0.5948, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 30.65, | |
| "learning_rate": 3.0829007633587785e-05, | |
| "loss": 0.5847, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 30.79, | |
| "learning_rate": 3.06e-05, | |
| "loss": 0.5768, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "learning_rate": 3.0370992366412212e-05, | |
| "loss": 0.5706, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "eval_loss": 0.1035308688879013, | |
| "eval_runtime": 56.4523, | |
| "eval_samples_per_second": 8.078, | |
| "eval_steps_per_second": 1.01, | |
| "eval_wer": 0.10374509211718513, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 31.08, | |
| "learning_rate": 3.0141984732824422e-05, | |
| "loss": 0.5819, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 31.22, | |
| "learning_rate": 2.991297709923664e-05, | |
| "loss": 0.5529, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 31.37, | |
| "learning_rate": 2.9683969465648852e-05, | |
| "loss": 0.5691, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 31.51, | |
| "learning_rate": 2.9454961832061066e-05, | |
| "loss": 0.5622, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 31.65, | |
| "learning_rate": 2.922595419847328e-05, | |
| "loss": 0.5555, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 31.65, | |
| "eval_loss": 0.10311654210090637, | |
| "eval_runtime": 56.2781, | |
| "eval_samples_per_second": 8.103, | |
| "eval_steps_per_second": 1.013, | |
| "eval_wer": 0.09272123225611598, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 2.8996946564885493e-05, | |
| "loss": 0.5697, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "learning_rate": 2.8767938931297706e-05, | |
| "loss": 0.5567, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 32.09, | |
| "learning_rate": 2.8538931297709923e-05, | |
| "loss": 0.5562, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 32.23, | |
| "learning_rate": 2.8309923664122133e-05, | |
| "loss": 0.5482, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "learning_rate": 2.808091603053435e-05, | |
| "loss": 0.5389, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "eval_loss": 0.09973499178886414, | |
| "eval_runtime": 56.482, | |
| "eval_samples_per_second": 8.073, | |
| "eval_steps_per_second": 1.009, | |
| "eval_wer": 0.09000302023557838, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 2.785419847328244e-05, | |
| "loss": 0.5398, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 32.66, | |
| "learning_rate": 2.7625190839694654e-05, | |
| "loss": 0.5284, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "learning_rate": 2.739618320610687e-05, | |
| "loss": 0.5292, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 2.716717557251908e-05, | |
| "loss": 0.5186, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "learning_rate": 2.6938167938931298e-05, | |
| "loss": 0.5201, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "eval_loss": 0.09196200966835022, | |
| "eval_runtime": 56.8421, | |
| "eval_samples_per_second": 8.022, | |
| "eval_steps_per_second": 1.003, | |
| "eval_wer": 0.09121111446692842, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 33.24, | |
| "learning_rate": 2.6709160305343508e-05, | |
| "loss": 0.5205, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 33.38, | |
| "learning_rate": 2.648015267175572e-05, | |
| "loss": 0.5247, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 33.52, | |
| "learning_rate": 2.6251145038167938e-05, | |
| "loss": 0.5156, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 33.67, | |
| "learning_rate": 2.6022137404580148e-05, | |
| "loss": 0.5125, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 33.81, | |
| "learning_rate": 2.5793129770992365e-05, | |
| "loss": 0.5146, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 33.81, | |
| "eval_loss": 0.09293542802333832, | |
| "eval_runtime": 57.2076, | |
| "eval_samples_per_second": 7.971, | |
| "eval_steps_per_second": 0.996, | |
| "eval_wer": 0.0946843853820598, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 33.96, | |
| "learning_rate": 2.5564122137404575e-05, | |
| "loss": 0.5085, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 34.1, | |
| "learning_rate": 2.5335114503816792e-05, | |
| "loss": 0.5173, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 34.24, | |
| "learning_rate": 2.5106106870229002e-05, | |
| "loss": 0.5101, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 34.39, | |
| "learning_rate": 2.487709923664122e-05, | |
| "loss": 0.5056, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 34.53, | |
| "learning_rate": 2.4648091603053432e-05, | |
| "loss": 0.515, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 34.53, | |
| "eval_loss": 0.10004792362451553, | |
| "eval_runtime": 56.2386, | |
| "eval_samples_per_second": 8.108, | |
| "eval_steps_per_second": 1.014, | |
| "eval_wer": 0.09528843249773482, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 34.68, | |
| "learning_rate": 2.4419083969465646e-05, | |
| "loss": 0.5211, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 34.82, | |
| "learning_rate": 2.419007633587786e-05, | |
| "loss": 0.5065, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 34.96, | |
| "learning_rate": 2.3961068702290076e-05, | |
| "loss": 0.4992, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 2.3732061068702286e-05, | |
| "loss": 0.495, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 35.25, | |
| "learning_rate": 2.3503053435114503e-05, | |
| "loss": 0.4743, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 35.25, | |
| "eval_loss": 0.09216006845235825, | |
| "eval_runtime": 56.5494, | |
| "eval_samples_per_second": 8.064, | |
| "eval_steps_per_second": 1.008, | |
| "eval_wer": 0.0892479613409846, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "learning_rate": 2.3274045801526713e-05, | |
| "loss": 0.4769, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "learning_rate": 2.304503816793893e-05, | |
| "loss": 0.4774, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 35.68, | |
| "learning_rate": 2.28206106870229e-05, | |
| "loss": 0.487, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 35.83, | |
| "learning_rate": 2.259160305343511e-05, | |
| "loss": 0.4797, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 2.2362595419847328e-05, | |
| "loss": 0.4707, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "eval_loss": 0.08524981886148453, | |
| "eval_runtime": 56.8651, | |
| "eval_samples_per_second": 8.019, | |
| "eval_steps_per_second": 1.002, | |
| "eval_wer": 0.08079130172153429, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 36.11, | |
| "learning_rate": 2.2133587786259538e-05, | |
| "loss": 0.4668, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 36.26, | |
| "learning_rate": 2.1904580152671755e-05, | |
| "loss": 0.476, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 36.4, | |
| "learning_rate": 2.167557251908397e-05, | |
| "loss": 0.4609, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "learning_rate": 2.1446564885496182e-05, | |
| "loss": 0.4605, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 36.69, | |
| "learning_rate": 2.1217557251908395e-05, | |
| "loss": 0.4456, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 36.69, | |
| "eval_loss": 0.08548382669687271, | |
| "eval_runtime": 56.4053, | |
| "eval_samples_per_second": 8.084, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.07792207792207792, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 36.83, | |
| "learning_rate": 2.098854961832061e-05, | |
| "loss": 0.4515, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 36.98, | |
| "learning_rate": 2.0759541984732822e-05, | |
| "loss": 0.4426, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 37.12, | |
| "learning_rate": 2.053053435114504e-05, | |
| "loss": 0.4491, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 37.27, | |
| "learning_rate": 2.030152671755725e-05, | |
| "loss": 0.4464, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 37.41, | |
| "learning_rate": 2.0072519083969466e-05, | |
| "loss": 0.443, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 37.41, | |
| "eval_loss": 0.0842847004532814, | |
| "eval_runtime": 56.5582, | |
| "eval_samples_per_second": 8.062, | |
| "eval_steps_per_second": 1.008, | |
| "eval_wer": 0.07384475989127152, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 37.55, | |
| "learning_rate": 1.9843511450381676e-05, | |
| "loss": 0.4381, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "learning_rate": 1.9614503816793893e-05, | |
| "loss": 0.4311, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 37.84, | |
| "learning_rate": 1.9385496183206106e-05, | |
| "loss": 0.4413, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 37.98, | |
| "learning_rate": 1.915648854961832e-05, | |
| "loss": 0.4186, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 38.13, | |
| "learning_rate": 1.8927480916030533e-05, | |
| "loss": 0.4388, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 38.13, | |
| "eval_loss": 0.081607885658741, | |
| "eval_runtime": 56.5857, | |
| "eval_samples_per_second": 8.059, | |
| "eval_steps_per_second": 1.007, | |
| "eval_wer": 0.06991845363938387, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 38.27, | |
| "learning_rate": 1.8698473282442747e-05, | |
| "loss": 0.4181, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 38.42, | |
| "learning_rate": 1.846946564885496e-05, | |
| "loss": 0.4338, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 38.56, | |
| "learning_rate": 1.8240458015267174e-05, | |
| "loss": 0.4186, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 38.7, | |
| "learning_rate": 1.8011450381679387e-05, | |
| "loss": 0.4169, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "learning_rate": 1.77824427480916e-05, | |
| "loss": 0.4162, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "eval_loss": 0.07516241818666458, | |
| "eval_runtime": 56.61, | |
| "eval_samples_per_second": 8.055, | |
| "eval_steps_per_second": 1.007, | |
| "eval_wer": 0.06448202959830866, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "learning_rate": 1.7553435114503814e-05, | |
| "loss": 0.4076, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 39.14, | |
| "learning_rate": 1.7324427480916027e-05, | |
| "loss": 0.4073, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 39.28, | |
| "learning_rate": 1.7095419847328244e-05, | |
| "loss": 0.4042, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 39.42, | |
| "learning_rate": 1.6866412213740458e-05, | |
| "loss": 0.4035, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 1.663740458015267e-05, | |
| "loss": 0.3979, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "eval_loss": 0.07611743360757828, | |
| "eval_runtime": 56.1996, | |
| "eval_samples_per_second": 8.114, | |
| "eval_steps_per_second": 1.014, | |
| "eval_wer": 0.062065841135608577, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 39.71, | |
| "learning_rate": 1.6408396946564885e-05, | |
| "loss": 0.3923, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 1.6179389312977098e-05, | |
| "loss": 0.395, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.595038167938931e-05, | |
| "loss": 0.3931, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 1.5721374045801525e-05, | |
| "loss": 0.3969, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 40.29, | |
| "learning_rate": 1.549236641221374e-05, | |
| "loss": 0.3889, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 40.29, | |
| "eval_loss": 0.07714105397462845, | |
| "eval_runtime": 56.3655, | |
| "eval_samples_per_second": 8.09, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.06251887647236484, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 1.5263358778625952e-05, | |
| "loss": 0.387, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 40.57, | |
| "learning_rate": 1.5034351145038167e-05, | |
| "loss": 0.3911, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 40.72, | |
| "learning_rate": 1.480534351145038e-05, | |
| "loss": 0.3865, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 40.86, | |
| "learning_rate": 1.4576335877862594e-05, | |
| "loss": 0.382, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.4347328244274809e-05, | |
| "loss": 0.3923, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "eval_loss": 0.07554154098033905, | |
| "eval_runtime": 57.0575, | |
| "eval_samples_per_second": 7.992, | |
| "eval_steps_per_second": 0.999, | |
| "eval_wer": 0.059800664451827246, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 41.15, | |
| "learning_rate": 1.4118320610687023e-05, | |
| "loss": 0.3723, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 41.29, | |
| "learning_rate": 1.3889312977099236e-05, | |
| "loss": 0.3797, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 41.44, | |
| "learning_rate": 1.3662595419847327e-05, | |
| "loss": 0.3823, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 41.58, | |
| "learning_rate": 1.343358778625954e-05, | |
| "loss": 0.3691, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 41.73, | |
| "learning_rate": 1.3204580152671754e-05, | |
| "loss": 0.3693, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 41.73, | |
| "eval_loss": 0.07298705726861954, | |
| "eval_runtime": 59.4935, | |
| "eval_samples_per_second": 7.665, | |
| "eval_steps_per_second": 0.958, | |
| "eval_wer": 0.05783751132588342, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 41.87, | |
| "learning_rate": 1.2975572519083969e-05, | |
| "loss": 0.3739, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 1.2746564885496182e-05, | |
| "loss": 0.3797, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 42.16, | |
| "learning_rate": 1.2517557251908396e-05, | |
| "loss": 0.3704, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 42.3, | |
| "learning_rate": 1.2288549618320609e-05, | |
| "loss": 0.3702, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "learning_rate": 1.2059541984732823e-05, | |
| "loss": 0.3642, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "eval_loss": 0.07388342171907425, | |
| "eval_runtime": 56.6481, | |
| "eval_samples_per_second": 8.05, | |
| "eval_steps_per_second": 1.006, | |
| "eval_wer": 0.059800664451827246, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "learning_rate": 1.1830534351145038e-05, | |
| "loss": 0.3665, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 42.73, | |
| "learning_rate": 1.1601526717557251e-05, | |
| "loss": 0.3626, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 42.88, | |
| "learning_rate": 1.1372519083969465e-05, | |
| "loss": 0.3499, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 1.1143511450381678e-05, | |
| "loss": 0.3632, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 43.17, | |
| "learning_rate": 1.0914503816793893e-05, | |
| "loss": 0.3532, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 43.17, | |
| "eval_loss": 0.07121992111206055, | |
| "eval_runtime": 57.0783, | |
| "eval_samples_per_second": 7.989, | |
| "eval_steps_per_second": 0.999, | |
| "eval_wer": 0.05527031108426457, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 43.31, | |
| "learning_rate": 1.0685496183206107e-05, | |
| "loss": 0.3531, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 43.45, | |
| "learning_rate": 1.045648854961832e-05, | |
| "loss": 0.361, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 1.0227480916030534e-05, | |
| "loss": 0.3508, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 43.74, | |
| "learning_rate": 9.998473282442747e-06, | |
| "loss": 0.352, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 43.88, | |
| "learning_rate": 9.769465648854962e-06, | |
| "loss": 0.3513, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 43.88, | |
| "eval_loss": 0.07616806775331497, | |
| "eval_runtime": 56.3541, | |
| "eval_samples_per_second": 8.092, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.051646028390214434, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 44.03, | |
| "learning_rate": 9.540458015267176e-06, | |
| "loss": 0.3447, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 44.17, | |
| "learning_rate": 9.311450381679389e-06, | |
| "loss": 0.3463, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 44.32, | |
| "learning_rate": 9.082442748091603e-06, | |
| "loss": 0.3373, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 44.46, | |
| "learning_rate": 8.855725190839693e-06, | |
| "loss": 0.3419, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "learning_rate": 8.626717557251907e-06, | |
| "loss": 0.3349, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "eval_loss": 0.07309506088495255, | |
| "eval_runtime": 56.1703, | |
| "eval_samples_per_second": 8.118, | |
| "eval_steps_per_second": 1.015, | |
| "eval_wer": 0.05043793415886439, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 44.75, | |
| "learning_rate": 8.397709923664122e-06, | |
| "loss": 0.3352, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "learning_rate": 8.168702290076335e-06, | |
| "loss": 0.3376, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 45.04, | |
| "learning_rate": 7.939694656488549e-06, | |
| "loss": 0.3361, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 45.18, | |
| "learning_rate": 7.710687022900762e-06, | |
| "loss": 0.3318, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 7.4816793893129765e-06, | |
| "loss": 0.3305, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "eval_loss": 0.0724666640162468, | |
| "eval_runtime": 58.1784, | |
| "eval_samples_per_second": 7.838, | |
| "eval_steps_per_second": 0.98, | |
| "eval_wer": 0.0507399577167019, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 45.47, | |
| "learning_rate": 7.25267175572519e-06, | |
| "loss": 0.3218, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 45.61, | |
| "learning_rate": 7.0259541984732824e-06, | |
| "loss": 0.3254, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 45.75, | |
| "learning_rate": 6.799236641221373e-06, | |
| "loss": 0.3256, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 45.9, | |
| "learning_rate": 6.570229007633587e-06, | |
| "loss": 0.3198, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 46.04, | |
| "learning_rate": 6.341221374045801e-06, | |
| "loss": 0.3285, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 46.04, | |
| "eval_loss": 0.07090699672698975, | |
| "eval_runtime": 59.4451, | |
| "eval_samples_per_second": 7.671, | |
| "eval_steps_per_second": 0.959, | |
| "eval_wer": 0.04892781636967684, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 46.19, | |
| "learning_rate": 6.112213740458014e-06, | |
| "loss": 0.323, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 46.33, | |
| "learning_rate": 5.883206106870229e-06, | |
| "loss": 0.3175, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 5.654198473282442e-06, | |
| "loss": 0.3191, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 46.62, | |
| "learning_rate": 5.425190839694656e-06, | |
| "loss": 0.313, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "learning_rate": 5.19618320610687e-06, | |
| "loss": 0.3179, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "eval_loss": 0.06665544956922531, | |
| "eval_runtime": 56.3776, | |
| "eval_samples_per_second": 8.088, | |
| "eval_steps_per_second": 1.011, | |
| "eval_wer": 0.0466626396858955, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 46.91, | |
| "learning_rate": 4.967175572519083e-06, | |
| "loss": 0.316, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 47.05, | |
| "learning_rate": 4.738167938931298e-06, | |
| "loss": 0.3107, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 47.19, | |
| "learning_rate": 4.509160305343511e-06, | |
| "loss": 0.3094, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 47.34, | |
| "learning_rate": 4.2801526717557246e-06, | |
| "loss": 0.3161, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 47.48, | |
| "learning_rate": 4.051145038167939e-06, | |
| "loss": 0.3158, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 47.48, | |
| "eval_loss": 0.06528327614068985, | |
| "eval_runtime": 56.0724, | |
| "eval_samples_per_second": 8.132, | |
| "eval_steps_per_second": 1.017, | |
| "eval_wer": 0.0493808517064331, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 47.63, | |
| "learning_rate": 3.822137404580152e-06, | |
| "loss": 0.3153, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 47.77, | |
| "learning_rate": 3.593129770992366e-06, | |
| "loss": 0.3005, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 3.36412213740458e-06, | |
| "loss": 0.3089, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 48.06, | |
| "learning_rate": 3.135114503816794e-06, | |
| "loss": 0.3068, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 48.2, | |
| "learning_rate": 2.906106870229007e-06, | |
| "loss": 0.3033, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 48.2, | |
| "eval_loss": 0.06382497400045395, | |
| "eval_runtime": 57.4782, | |
| "eval_samples_per_second": 7.933, | |
| "eval_steps_per_second": 0.992, | |
| "eval_wer": 0.04560555723346421, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 48.34, | |
| "learning_rate": 2.677099236641221e-06, | |
| "loss": 0.3039, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 48.49, | |
| "learning_rate": 2.4480916030534347e-06, | |
| "loss": 0.2983, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 48.63, | |
| "learning_rate": 2.219083969465649e-06, | |
| "loss": 0.3069, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 48.78, | |
| "learning_rate": 1.9900763358778624e-06, | |
| "loss": 0.2987, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "learning_rate": 1.761068702290076e-06, | |
| "loss": 0.3023, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_loss": 0.06439350545406342, | |
| "eval_runtime": 56.5994, | |
| "eval_samples_per_second": 8.057, | |
| "eval_steps_per_second": 1.007, | |
| "eval_wer": 0.04636061612805799, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 49.06, | |
| "learning_rate": 1.53206106870229e-06, | |
| "loss": 0.2919, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 49.21, | |
| "learning_rate": 1.3030534351145036e-06, | |
| "loss": 0.2912, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 49.35, | |
| "learning_rate": 1.0740458015267175e-06, | |
| "loss": 0.3036, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 49.5, | |
| "learning_rate": 8.450381679389312e-07, | |
| "loss": 0.3025, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 49.64, | |
| "learning_rate": 6.160305343511449e-07, | |
| "loss": 0.2975, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 49.64, | |
| "eval_loss": 0.06428828090429306, | |
| "eval_runtime": 56.8585, | |
| "eval_samples_per_second": 8.02, | |
| "eval_steps_per_second": 1.002, | |
| "eval_wer": 0.045454545454545456, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 49.78, | |
| "learning_rate": 3.8702290076335876e-07, | |
| "loss": 0.2955, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 49.93, | |
| "learning_rate": 1.580152671755725e-07, | |
| "loss": 0.2952, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 34750, | |
| "total_flos": 8.643412752890073e+20, | |
| "train_loss": 1.0736439298451375, | |
| "train_runtime": 194988.743, | |
| "train_samples_per_second": 5.709, | |
| "train_steps_per_second": 0.178 | |
| } | |
| ], | |
| "max_steps": 34750, | |
| "num_train_epochs": 50, | |
| "total_flos": 8.643412752890073e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |