| { | |
| "best_metric": 30.84976675148431, | |
| "best_model_checkpoint": "Models/whisper-small-sv-test\\checkpoint-4500", | |
| "epoch": 7.662835249042145, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 4.5853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 3.8977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.42e-06, | |
| "loss": 3.0188, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 2.0302, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.42e-06, | |
| "loss": 1.5475, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.92e-06, | |
| "loss": 1.4042, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 1.2769, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 1.2072, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.42e-06, | |
| "loss": 1.0967, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.9673, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.8524, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.6938, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.6267, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.5576, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.521, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.5202, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.5577, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.5422, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.4767, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.5133, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.5561969876289368, | |
| "eval_runtime": 853.2098, | |
| "eval_samples_per_second": 6.001, | |
| "eval_steps_per_second": 0.375, | |
| "eval_wer": 38.38263358778626, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5319, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5129, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4844, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5227, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4742, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4679, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4982, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5005, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4669, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4893, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4736, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3817, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3355, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3759, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3723, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3371, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3349, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3017, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3651, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3764, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.4754212498664856, | |
| "eval_runtime": 857.1629, | |
| "eval_samples_per_second": 5.973, | |
| "eval_steps_per_second": 0.373, | |
| "eval_wer": 34.19211195928753, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3347, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3007, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3481, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3436, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3301, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3334, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3302, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3488, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3187, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3301, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3381, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.32, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3019, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3196, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3133, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3073, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3174, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.341, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3369, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3501, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.4553873538970947, | |
| "eval_runtime": 1065.4964, | |
| "eval_samples_per_second": 4.805, | |
| "eval_steps_per_second": 0.3, | |
| "eval_wer": 32.85093299406277, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3232, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3362, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.292, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2248, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2137, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.236, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2277, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2274, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2323, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2115, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2313, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2188, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2055, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2399, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1984, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.205, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2083, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2112, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2179, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.222, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.4399167001247406, | |
| "eval_runtime": 1074.0114, | |
| "eval_samples_per_second": 4.767, | |
| "eval_steps_per_second": 0.298, | |
| "eval_wer": 32.384435962680236, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2211, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2282, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2289, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2126, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2387, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2226, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2188, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2133, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2018, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2216, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2281, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2426, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.237, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.224, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1461, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1451, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1502, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1541, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1543, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1283, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.4439845085144043, | |
| "eval_runtime": 1066.7958, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.3, | |
| "eval_wer": 32.00805767599661, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1542, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1556, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1522, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1376, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1715, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1435, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1487, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.154, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.168, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1453, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1451, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1533, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1688, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1385, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1603, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1538, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1519, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1427, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1718, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1575, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 0.42946428060531616, | |
| "eval_runtime": 1069.9631, | |
| "eval_samples_per_second": 4.785, | |
| "eval_steps_per_second": 0.299, | |
| "eval_wer": 31.822519083969464, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1595, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1521, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1573, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1606, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1634, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1109, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1189, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0945, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1087, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.111, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.116, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1058, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.118, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.114, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1039, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1066, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1133, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1149, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1278, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1205, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_loss": 0.44103145599365234, | |
| "eval_runtime": 1067.3863, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 0.3, | |
| "eval_wer": 31.045907548770145, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1202, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1144, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.126, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1214, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1028, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.119, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1265, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1128, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1165, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1191, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1224, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1203, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1108, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1117, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1055, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.117, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0996, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0777, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0879, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0992, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_loss": 0.4505476951599121, | |
| "eval_runtime": 1061.7946, | |
| "eval_samples_per_second": 4.822, | |
| "eval_steps_per_second": 0.301, | |
| "eval_wer": 31.104219677692964, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0817, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0845, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0817, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0819, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0932, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0946, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0925, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1049, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0983, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0869, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0882, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0872, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0933, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0888, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.095, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0905, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0721, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1014, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1145, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0941, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_loss": 0.4550601840019226, | |
| "eval_runtime": 1063.5349, | |
| "eval_samples_per_second": 4.814, | |
| "eval_steps_per_second": 0.301, | |
| "eval_wer": 30.84976675148431, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0949, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0877, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 1e-05, | |
| "loss": 0.089, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0886, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0925, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0918, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1015, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0795, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0663, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.08, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0744, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0735, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0729, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0728, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0561, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0819, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0845, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0648, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0642, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0627, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 0.46955546736717224, | |
| "eval_runtime": 1062.3461, | |
| "eval_samples_per_second": 4.82, | |
| "eval_steps_per_second": 0.301, | |
| "eval_wer": 31.599872773536898, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0751, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0859, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0748, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0691, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0749, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0791, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0742, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0779, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0797, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0682, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0623, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0755, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0715, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0703, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0806, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0667, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0774, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0828, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0775, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0652, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_loss": 0.4761393964290619, | |
| "eval_runtime": 1071.382, | |
| "eval_samples_per_second": 4.779, | |
| "eval_steps_per_second": 0.299, | |
| "eval_wer": 31.80131467345208, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0575, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0504, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0434, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0526, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0553, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0588, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0737, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0626, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0564, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0566, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0578, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0558, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0542, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0506, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0582, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0645, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0616, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0525, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0687, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0573, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "eval_loss": 0.48460179567337036, | |
| "eval_runtime": 1063.3016, | |
| "eval_samples_per_second": 4.815, | |
| "eval_steps_per_second": 0.301, | |
| "eval_wer": 30.900127226463102, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 6000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "total_flos": 2.769005774610432e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |