Invalid JSON: Unexpected token 'N', ..."al_loss": NaN,
"... is not valid JSON
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.999677731227845, | |
| "global_step": 23265, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.950000000000001e-06, | |
| "loss": 9.3801, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.85e-06, | |
| "loss": 8.1479, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.485e-05, | |
| "loss": 4.0405, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.985e-05, | |
| "loss": 3.1569, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.485e-05, | |
| "loss": 2.9728, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 2.9448530673980713, | |
| "eval_runtime": 378.7996, | |
| "eval_samples_per_second": 14.353, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.985e-05, | |
| "loss": 2.9272, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.485e-05, | |
| "loss": 2.9, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3.9850000000000006e-05, | |
| "loss": 2.888, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.4850000000000006e-05, | |
| "loss": 2.8488, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.9850000000000006e-05, | |
| "loss": 2.5099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.8491624593734741, | |
| "eval_runtime": 377.919, | |
| "eval_samples_per_second": 14.387, | |
| "eval_steps_per_second": 0.9, | |
| "eval_wer": 0.9910086579662114, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.485e-05, | |
| "loss": 1.6261, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.9850000000000005e-05, | |
| "loss": 1.1446, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.485e-05, | |
| "loss": 0.9612, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.98e-05, | |
| "loss": 0.8481, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.48e-05, | |
| "loss": 0.7872, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.44667136669158936, | |
| "eval_runtime": 377.5063, | |
| "eval_samples_per_second": 14.402, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.37744026199417574, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.98e-05, | |
| "loss": 0.7204, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 8.48e-05, | |
| "loss": 0.698, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.98e-05, | |
| "loss": 0.6488, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.475e-05, | |
| "loss": 0.6333, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 9.975000000000001e-05, | |
| "loss": 0.5993, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.31809717416763306, | |
| "eval_runtime": 384.016, | |
| "eval_samples_per_second": 14.158, | |
| "eval_steps_per_second": 0.885, | |
| "eval_wer": 0.2819476992165668, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.955325652480602e-05, | |
| "loss": 0.5798, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.908300023512816e-05, | |
| "loss": 0.5414, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.861274394545027e-05, | |
| "loss": 0.5285, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.81424876557724e-05, | |
| "loss": 0.6176, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.767223136609452e-05, | |
| "loss": 0.5134, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.2638131380081177, | |
| "eval_runtime": 377.43, | |
| "eval_samples_per_second": 14.405, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.24006000764803356, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.720197507641666e-05, | |
| "loss": 0.4847, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 9.673171878673878e-05, | |
| "loss": 0.4825, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 9.62614624970609e-05, | |
| "loss": 0.476, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.579120620738303e-05, | |
| "loss": 0.4645, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.532094991770515e-05, | |
| "loss": 0.4544, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.22873832285404205, | |
| "eval_runtime": 377.8259, | |
| "eval_samples_per_second": 14.39, | |
| "eval_steps_per_second": 0.9, | |
| "eval_wer": 0.2091246923627521, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.485069362802728e-05, | |
| "loss": 0.453, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.43804373383494e-05, | |
| "loss": 0.4392, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.391018104867153e-05, | |
| "loss": 0.4275, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.343992475899366e-05, | |
| "loss": 0.4119, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 9.296966846931579e-05, | |
| "loss": 0.4085, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.21533556282520294, | |
| "eval_runtime": 377.0477, | |
| "eval_samples_per_second": 14.42, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.1917891495974977, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.249941217963791e-05, | |
| "loss": 0.3964, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 9.202915588996003e-05, | |
| "loss": 0.3885, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.155889960028216e-05, | |
| "loss": 0.3915, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.108864331060428e-05, | |
| "loss": 0.4073, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.061838702092641e-05, | |
| "loss": 0.3921, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 0.20039014518260956, | |
| "eval_runtime": 376.6397, | |
| "eval_samples_per_second": 14.436, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.18042495612185866, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.015283329414532e-05, | |
| "loss": 0.3795, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 8.968257700446744e-05, | |
| "loss": 0.3866, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 8.921232071478956e-05, | |
| "loss": 0.3692, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 8.874206442511169e-05, | |
| "loss": 0.373, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 8.827180813543383e-05, | |
| "loss": 0.4613, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.19046556949615479, | |
| "eval_runtime": 376.5699, | |
| "eval_samples_per_second": 14.438, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.17323776559757617, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 8.780155184575594e-05, | |
| "loss": 0.3563, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.733129555607806e-05, | |
| "loss": 0.3491, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 8.686103926640018e-05, | |
| "loss": 0.3391, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.639078297672232e-05, | |
| "loss": 0.3459, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 8.592052668704445e-05, | |
| "loss": 0.3402, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_loss": 0.17775115370750427, | |
| "eval_runtime": 374.7655, | |
| "eval_samples_per_second": 14.508, | |
| "eval_steps_per_second": 0.907, | |
| "eval_wer": 0.1658936923333366, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 8.545027039736657e-05, | |
| "loss": 0.3317, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 8.49800141076887e-05, | |
| "loss": 0.3284, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 8.450975781801082e-05, | |
| "loss": 0.3231, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 8.403950152833294e-05, | |
| "loss": 0.3284, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 8.356924523865507e-05, | |
| "loss": 0.3258, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 0.17322729527950287, | |
| "eval_runtime": 379.1854, | |
| "eval_samples_per_second": 14.339, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.15707884338199968, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 8.309898894897719e-05, | |
| "loss": 0.3334, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 8.262873265929933e-05, | |
| "loss": 0.3186, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 8.215847636962145e-05, | |
| "loss": 0.3145, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 8.168822007994358e-05, | |
| "loss": 0.3208, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 8.122266635316248e-05, | |
| "loss": 0.3044, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 0.16769851744174957, | |
| "eval_runtime": 377.3431, | |
| "eval_samples_per_second": 14.409, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.1497249649465128, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 8.075241006348461e-05, | |
| "loss": 0.3189, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.028215377380672e-05, | |
| "loss": 0.4003, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.981189748412886e-05, | |
| "loss": 0.3851, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 7.934164119445098e-05, | |
| "loss": 0.297, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 7.88713849047731e-05, | |
| "loss": 0.2914, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 0.15965130925178528, | |
| "eval_runtime": 376.7695, | |
| "eval_samples_per_second": 14.431, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.1420475158598645, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 7.840112861509523e-05, | |
| "loss": 0.2895, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.793557488831414e-05, | |
| "loss": 0.2979, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 7.746531859863626e-05, | |
| "loss": 0.2951, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 7.699506230895838e-05, | |
| "loss": 0.294, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.652480601928051e-05, | |
| "loss": 0.278, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 0.15744146704673767, | |
| "eval_runtime": 378.117, | |
| "eval_samples_per_second": 14.379, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.13855687489582005, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 7.605454972960265e-05, | |
| "loss": 0.2823, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 7.558429343992476e-05, | |
| "loss": 0.2865, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 7.511403715024688e-05, | |
| "loss": 0.2698, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 7.464378086056902e-05, | |
| "loss": 0.2951, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 7.417352457089114e-05, | |
| "loss": 0.2858, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "eval_loss": 0.15517516434192657, | |
| "eval_runtime": 376.387, | |
| "eval_samples_per_second": 14.445, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.12995773971192406, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 7.370326828121327e-05, | |
| "loss": 0.2851, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 7.323301199153539e-05, | |
| "loss": 0.2814, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.276275570185751e-05, | |
| "loss": 0.2662, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 7.229249941217964e-05, | |
| "loss": 0.2806, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 7.182224312250176e-05, | |
| "loss": 0.2585, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "eval_loss": 0.15228664875030518, | |
| "eval_runtime": 380.3124, | |
| "eval_samples_per_second": 14.296, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.12756527792757902, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 7.135198683282389e-05, | |
| "loss": 0.2699, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 7.088173054314602e-05, | |
| "loss": 0.2688, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 7.041147425346815e-05, | |
| "loss": 0.2686, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 6.994121796379027e-05, | |
| "loss": 0.2592, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 6.947096167411238e-05, | |
| "loss": 0.2827, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "eval_loss": 0.14475098252296448, | |
| "eval_runtime": 374.5535, | |
| "eval_samples_per_second": 14.516, | |
| "eval_steps_per_second": 0.908, | |
| "eval_wer": 0.12654554011785815, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 6.900070538443452e-05, | |
| "loss": 0.2587, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 6.853044909475665e-05, | |
| "loss": 0.2552, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 6.806019280507877e-05, | |
| "loss": 0.2679, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 6.75899365154009e-05, | |
| "loss": 0.2651, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 6.711968022572303e-05, | |
| "loss": 0.3365, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_loss": 0.14109323918819427, | |
| "eval_runtime": 377.5361, | |
| "eval_samples_per_second": 14.401, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.1232313922362654, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 6.664942393604515e-05, | |
| "loss": 0.2593, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 6.617916764636727e-05, | |
| "loss": 0.2495, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 6.571361391958619e-05, | |
| "loss": 0.2436, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 6.524335762990831e-05, | |
| "loss": 0.3209, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 6.477310134023042e-05, | |
| "loss": 0.2488, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 0.1456409990787506, | |
| "eval_runtime": 378.3904, | |
| "eval_samples_per_second": 14.369, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.11950542716228539, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 6.430284505055255e-05, | |
| "loss": 0.2393, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 6.383258876087468e-05, | |
| "loss": 0.2475, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 6.336233247119681e-05, | |
| "loss": 0.2339, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 6.289207618151893e-05, | |
| "loss": 0.2384, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 6.242181989184106e-05, | |
| "loss": 0.2406, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "eval_loss": 0.1413952112197876, | |
| "eval_runtime": 378.3628, | |
| "eval_samples_per_second": 14.37, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.11942698579230686, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 6.19515636021632e-05, | |
| "loss": 0.2518, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 6.14813073124853e-05, | |
| "loss": 0.2387, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 6.101105102280743e-05, | |
| "loss": 0.242, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 6.054079473312956e-05, | |
| "loss": 0.2409, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 6.007524100634846e-05, | |
| "loss": 0.2488, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_loss": 0.13929419219493866, | |
| "eval_runtime": 376.1627, | |
| "eval_samples_per_second": 14.454, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.11731887397413396, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 5.9604984716670584e-05, | |
| "loss": 0.2506, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 5.9134728426992715e-05, | |
| "loss": 0.2412, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 5.866447213731484e-05, | |
| "loss": 0.2414, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.819421584763697e-05, | |
| "loss": 0.251, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 5.7723959557959094e-05, | |
| "loss": 0.3084, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_loss": 0.13794787228107452, | |
| "eval_runtime": 376.7047, | |
| "eval_samples_per_second": 14.433, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.11644621373312285, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 5.725370326828121e-05, | |
| "loss": 0.2374, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 5.6783446978603336e-05, | |
| "loss": 0.2345, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 5.6313190688925466e-05, | |
| "loss": 0.2247, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 5.584293439924759e-05, | |
| "loss": 0.2367, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 5.537267810956972e-05, | |
| "loss": 0.2365, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 0.13865751028060913, | |
| "eval_runtime": 382.6889, | |
| "eval_samples_per_second": 14.207, | |
| "eval_steps_per_second": 0.888, | |
| "eval_wer": 0.11650504476060675, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 5.4902421819891845e-05, | |
| "loss": 0.2221, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 5.4432165530213976e-05, | |
| "loss": 0.2178, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 5.396661180343288e-05, | |
| "loss": 0.2296, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 5.3496355513755e-05, | |
| "loss": 0.2256, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 5.302609922407712e-05, | |
| "loss": 0.2217, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "eval_loss": 0.1380530297756195, | |
| "eval_runtime": 374.6191, | |
| "eval_samples_per_second": 14.513, | |
| "eval_steps_per_second": 0.908, | |
| "eval_wer": 0.11323992273525058, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 5.255584293439924e-05, | |
| "loss": 0.2296, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 5.2085586644721374e-05, | |
| "loss": 0.2326, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 5.16153303550435e-05, | |
| "loss": 0.227, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 5.114507406536563e-05, | |
| "loss": 0.2326, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 5.067481777568775e-05, | |
| "loss": 0.2381, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "eval_loss": 0.13600507378578186, | |
| "eval_runtime": 376.6806, | |
| "eval_samples_per_second": 14.434, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.11259278143292772, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 5.0204561486009884e-05, | |
| "loss": 0.2296, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 4.9734305196332e-05, | |
| "loss": 0.2185, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 4.926404890665413e-05, | |
| "loss": 0.2353, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.8793792616976256e-05, | |
| "loss": 0.2217, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 4.832353632729838e-05, | |
| "loss": 0.2329, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "eval_loss": 0.1356525719165802, | |
| "eval_runtime": 375.4068, | |
| "eval_samples_per_second": 14.483, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.11240648317922873, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 4.7853280037620504e-05, | |
| "loss": 0.2241, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.738302374794263e-05, | |
| "loss": 0.2256, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 4.691276745826476e-05, | |
| "loss": 0.2189, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.644251116858688e-05, | |
| "loss": 0.2932, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 4.597225487890901e-05, | |
| "loss": 0.2103, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_loss": 0.13354040682315826, | |
| "eval_runtime": 376.3349, | |
| "eval_samples_per_second": 14.447, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.10866090776275408, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 4.550199858923113e-05, | |
| "loss": 0.2253, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 4.503644486245004e-05, | |
| "loss": 0.2348, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 4.4566188572772164e-05, | |
| "loss": 0.2313, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.409593228309429e-05, | |
| "loss": 0.2333, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.362567599341641e-05, | |
| "loss": 0.2366, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 0.13876694440841675, | |
| "eval_runtime": 378.8799, | |
| "eval_samples_per_second": 14.35, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.11050427995724946, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.315541970373854e-05, | |
| "loss": 0.2322, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.268516341406067e-05, | |
| "loss": 0.3049, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 4.221490712438279e-05, | |
| "loss": 0.2376, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 4.1744650834704915e-05, | |
| "loss": 0.2289, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 4.127439454502704e-05, | |
| "loss": 0.2289, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "eval_loss": 0.13831551373004913, | |
| "eval_runtime": 376.3835, | |
| "eval_samples_per_second": 14.445, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.1097983076274427, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 4.080413825534917e-05, | |
| "loss": 0.2304, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 4.0333881965671294e-05, | |
| "loss": 0.2287, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 3.986362567599342e-05, | |
| "loss": 0.2348, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 3.939336938631554e-05, | |
| "loss": 0.2324, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 3.892311309663767e-05, | |
| "loss": 0.2486, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 0.1386488676071167, | |
| "eval_runtime": 381.3083, | |
| "eval_samples_per_second": 14.259, | |
| "eval_steps_per_second": 0.892, | |
| "eval_wer": 0.10869032327649603, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 3.84528568069598e-05, | |
| "loss": 0.2326, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 3.798260051728192e-05, | |
| "loss": 0.2364, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 3.7512344227604045e-05, | |
| "loss": 0.2519, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 3.7046790500822946e-05, | |
| "loss": 0.2615, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 3.657653421114508e-05, | |
| "loss": 0.2772, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_loss": 0.15979500114917755, | |
| "eval_runtime": 378.6086, | |
| "eval_samples_per_second": 14.36, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.10933746457881886, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 3.61062779214672e-05, | |
| "loss": 0.273, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 3.563602163178933e-05, | |
| "loss": 0.2799, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 3.516576534211145e-05, | |
| "loss": 0.2674, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 3.469550905243358e-05, | |
| "loss": 0.2784, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 3.4225252762755704e-05, | |
| "loss": 0.2728, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "eval_loss": 0.18136879801750183, | |
| "eval_runtime": 374.0064, | |
| "eval_samples_per_second": 14.537, | |
| "eval_steps_per_second": 0.909, | |
| "eval_wer": 0.1109651230058733, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 3.375499647307783e-05, | |
| "loss": 0.2874, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 3.328474018339995e-05, | |
| "loss": 0.316, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 3.2814483893722083e-05, | |
| "loss": 0.3058, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 3.2348930166940985e-05, | |
| "loss": 0.3039, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 3.187867387726311e-05, | |
| "loss": 0.3437, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "eval_loss": 0.25054600834846497, | |
| "eval_runtime": 375.3433, | |
| "eval_samples_per_second": 14.485, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.1123868728367341, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 3.140841758758524e-05, | |
| "loss": 0.3646, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 3.093816129790736e-05, | |
| "loss": 0.4111, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 3.0467905008229485e-05, | |
| "loss": 0.3842, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 2.9997648718551612e-05, | |
| "loss": 0.3806, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 2.952739242887374e-05, | |
| "loss": 0.431, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_loss": 0.28276580572128296, | |
| "eval_runtime": 375.6956, | |
| "eval_samples_per_second": 14.472, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 0.11427927088746605, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 2.905713613919586e-05, | |
| "loss": 0.3948, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 2.8586879849517988e-05, | |
| "loss": 0.391, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 2.8116623559840115e-05, | |
| "loss": 0.4083, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 2.764636727016224e-05, | |
| "loss": 0.4305, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 2.7176110980484367e-05, | |
| "loss": 0.3929, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "eval_loss": 0.29774826765060425, | |
| "eval_runtime": 382.3796, | |
| "eval_samples_per_second": 14.219, | |
| "eval_steps_per_second": 0.889, | |
| "eval_wer": 0.11490680184729427, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 2.670585469080649e-05, | |
| "loss": 0.4219, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 2.6235598401128615e-05, | |
| "loss": 0.4197, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 2.5765342111450742e-05, | |
| "loss": 0.4265, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 2.529508582177287e-05, | |
| "loss": 0.4829, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 2.4824829532094994e-05, | |
| "loss": 0.4396, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "eval_loss": 0.3197712004184723, | |
| "eval_runtime": 378.387, | |
| "eval_samples_per_second": 14.369, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.11699530332297253, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 2.43592758053139e-05, | |
| "loss": 0.4394, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 2.3889019515636023e-05, | |
| "loss": 0.5335, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 2.341876322595815e-05, | |
| "loss": 0.5873, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 2.2948506936280274e-05, | |
| "loss": 0.6076, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 2.24782506466024e-05, | |
| "loss": 0.59, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "eval_loss": 0.41584599018096924, | |
| "eval_runtime": 384.0446, | |
| "eval_samples_per_second": 14.157, | |
| "eval_steps_per_second": 0.885, | |
| "eval_wer": 0.1315265671114946, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 2.2007994356924526e-05, | |
| "loss": 0.6303, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 2.1537738067246653e-05, | |
| "loss": 0.6319, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 2.1067481777568777e-05, | |
| "loss": 0.6773, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 2.0601928050787682e-05, | |
| "loss": 0.6564, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 2.0131671761109806e-05, | |
| "loss": 0.7813, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "eval_loss": 0.6122739911079407, | |
| "eval_runtime": 374.3179, | |
| "eval_samples_per_second": 14.525, | |
| "eval_steps_per_second": 0.908, | |
| "eval_wer": 0.2208026513183053, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.9661415471431934e-05, | |
| "loss": 0.8561, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 1.9191159181754058e-05, | |
| "loss": 0.8639, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 1.8720902892076185e-05, | |
| "loss": 0.9351, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 1.825064660239831e-05, | |
| "loss": 0.9492, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 1.7780390312720433e-05, | |
| "loss": 0.9345, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "eval_loss": 0.6814701557159424, | |
| "eval_runtime": 375.5048, | |
| "eval_samples_per_second": 14.479, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 0.28850735878102113, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 1.731013402304256e-05, | |
| "loss": 0.9227, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 1.6839877733364685e-05, | |
| "loss": 0.9694, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 1.6369621443686812e-05, | |
| "loss": 0.9394, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 1.5936985657183166e-05, | |
| "loss": 0.9483, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 1.5518457559369855e-05, | |
| "loss": 0.998, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "eval_loss": 0.7587289214134216, | |
| "eval_runtime": 378.2354, | |
| "eval_samples_per_second": 14.375, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.19911361251924264, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 1.5104632024453328e-05, | |
| "loss": 1.0172, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.4667293675052904e-05, | |
| "loss": 0.999, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 1.4253468140136376e-05, | |
| "loss": 1.0465, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 1.3839642605219846e-05, | |
| "loss": 1.0361, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 1.3421114507406538e-05, | |
| "loss": 1.0493, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "eval_loss": 0.7583341598510742, | |
| "eval_runtime": 375.5467, | |
| "eval_samples_per_second": 14.478, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 0.1996430917665977, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 1.3026099224077124e-05, | |
| "loss": 1.0257, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 1.2607571126263815e-05, | |
| "loss": 0.9884, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 1.217963790265695e-05, | |
| "loss": 0.9969, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 1.1775217493533977e-05, | |
| "loss": 1.0021, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 13.54, | |
| "learning_rate": 1.1441335527862685e-05, | |
| "loss": 1.438, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 13.54, | |
| "eval_loss": NaN, | |
| "eval_runtime": 375.5955, | |
| "eval_samples_per_second": 14.476, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 1.0, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 1.0971079238184811e-05, | |
| "loss": 0.0, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 1.0500822948506937e-05, | |
| "loss": 0.0, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 1.0030566658829062e-05, | |
| "loss": 0.0, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 9.560310369151188e-06, | |
| "loss": 0.0, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 9.090054079473314e-06, | |
| "loss": 0.0, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 369.5033, | |
| "eval_samples_per_second": 14.714, | |
| "eval_steps_per_second": 0.92, | |
| "eval_wer": 1.0, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 8.61979778979544e-06, | |
| "loss": 0.0, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 8.149541500117565e-06, | |
| "loss": 0.0, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 7.679285210439691e-06, | |
| "loss": 0.0, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 7.209028920761815e-06, | |
| "loss": 0.0, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 6.738772631083941e-06, | |
| "loss": 0.0, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "eval_loss": NaN, | |
| "eval_runtime": 375.3678, | |
| "eval_samples_per_second": 14.484, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 1.0, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 6.268516341406067e-06, | |
| "loss": 0.0, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 5.798260051728193e-06, | |
| "loss": 0.0, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 5.3280037620503175e-06, | |
| "loss": 0.0, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 4.857747472372443e-06, | |
| "loss": 0.0, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 4.387491182694569e-06, | |
| "loss": 0.0, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 371.6568, | |
| "eval_samples_per_second": 14.629, | |
| "eval_steps_per_second": 0.915, | |
| "eval_wer": 1.0, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 3.917234893016694e-06, | |
| "loss": 0.0, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 3.4469786033388197e-06, | |
| "loss": 0.0, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 2.9767223136609455e-06, | |
| "loss": 0.0, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 2.506466023983071e-06, | |
| "loss": 0.0, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 2.0362097343051966e-06, | |
| "loss": 0.0, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 369.8493, | |
| "eval_samples_per_second": 14.701, | |
| "eval_steps_per_second": 0.919, | |
| "eval_wer": 1.0, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 1.565953444627322e-06, | |
| "loss": 0.0, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 1.0956971549494475e-06, | |
| "loss": 0.0, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 23265, | |
| "total_flos": 1.618046661664003e+20, | |
| "train_loss": 0.5419238063665506, | |
| "train_runtime": 74160.538, | |
| "train_samples_per_second": 10.041, | |
| "train_steps_per_second": 0.314 | |
| } | |
| ], | |
| "max_steps": 23265, | |
| "num_train_epochs": 15, | |
| "total_flos": 1.618046661664003e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |