| { | |
| "best_metric": 9.396988496177238, | |
| "best_model_checkpoint": "./checkpoint-4000", | |
| "epoch": 2.23, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 1.5387, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 1.3488, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.42e-06, | |
| "loss": 0.8161, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 0.498, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.42e-06, | |
| "loss": 0.3711, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.3092, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.2652, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.2263, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.2451, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9000000000000005e-06, | |
| "loss": 0.227, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 0.2083, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5.9e-06, | |
| "loss": 0.1479, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.1947, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 6.9e-06, | |
| "loss": 0.3045, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 7.4e-06, | |
| "loss": 0.3406, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 7.9e-06, | |
| "loss": 0.3461, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.3167, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.900000000000001e-06, | |
| "loss": 0.2418, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.3031, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.9e-06, | |
| "loss": 0.6144, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.2794555425643921, | |
| "eval_runtime": 1731.7352, | |
| "eval_samples_per_second": 2.587, | |
| "eval_steps_per_second": 0.081, | |
| "eval_wer": 14.073652895247186, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.942857142857145e-06, | |
| "loss": 0.594, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.871428571428572e-06, | |
| "loss": 0.4331, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 0.3505, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.72857142857143e-06, | |
| "loss": 0.2652, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.657142857142859e-06, | |
| "loss": 0.2585, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.585714285714286e-06, | |
| "loss": 0.4135, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.514285714285715e-06, | |
| "loss": 0.5708, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.442857142857144e-06, | |
| "loss": 0.3726, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.374285714285715e-06, | |
| "loss": 0.2625, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.302857142857144e-06, | |
| "loss": 0.2396, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.231428571428573e-06, | |
| "loss": 0.2445, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.16e-06, | |
| "loss": 0.2828, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.08857142857143e-06, | |
| "loss": 0.2256, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.017142857142858e-06, | |
| "loss": 0.2214, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.945714285714286e-06, | |
| "loss": 0.1915, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.874285714285715e-06, | |
| "loss": 0.2015, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.802857142857144e-06, | |
| "loss": 0.2196, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.731428571428571e-06, | |
| "loss": 0.2346, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.66e-06, | |
| "loss": 0.2013, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.588571428571429e-06, | |
| "loss": 0.1643, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.2213420271873474, | |
| "eval_runtime": 1735.8972, | |
| "eval_samples_per_second": 2.581, | |
| "eval_steps_per_second": 0.081, | |
| "eval_wer": 11.491638660154942, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.517142857142858e-06, | |
| "loss": 0.1507, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.445714285714285e-06, | |
| "loss": 0.2044, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.374285714285714e-06, | |
| "loss": 0.1698, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.302857142857143e-06, | |
| "loss": 0.1577, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.231428571428572e-06, | |
| "loss": 0.2725, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.16e-06, | |
| "loss": 0.354, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.088571428571429e-06, | |
| "loss": 0.4204, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.017142857142858e-06, | |
| "loss": 0.2924, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.945714285714287e-06, | |
| "loss": 0.2252, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.874285714285716e-06, | |
| "loss": 0.2221, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.802857142857143e-06, | |
| "loss": 0.1945, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.731428571428572e-06, | |
| "loss": 0.2151, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.660000000000001e-06, | |
| "loss": 0.2168, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.588571428571429e-06, | |
| "loss": 0.2256, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.5171428571428575e-06, | |
| "loss": 0.1883, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.445714285714286e-06, | |
| "loss": 0.1894, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.374285714285715e-06, | |
| "loss": 0.1798, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.302857142857144e-06, | |
| "loss": 0.2096, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.231428571428573e-06, | |
| "loss": 0.1906, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.16e-06, | |
| "loss": 0.2175, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.2009447067975998, | |
| "eval_runtime": 1739.6156, | |
| "eval_samples_per_second": 2.575, | |
| "eval_steps_per_second": 0.08, | |
| "eval_wer": 10.002132217811125, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.088571428571429e-06, | |
| "loss": 0.2645, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.017142857142858e-06, | |
| "loss": 0.1904, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.945714285714287e-06, | |
| "loss": 0.109, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.874285714285714e-06, | |
| "loss": 0.1449, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 6.8028571428571434e-06, | |
| "loss": 0.1633, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.7314285714285724e-06, | |
| "loss": 0.2946, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.660000000000001e-06, | |
| "loss": 0.3049, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 6.588571428571429e-06, | |
| "loss": 0.1726, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 6.517142857142858e-06, | |
| "loss": 0.1232, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 6.445714285714286e-06, | |
| "loss": 0.0528, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 6.374285714285715e-06, | |
| "loss": 0.0516, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 6.302857142857144e-06, | |
| "loss": 0.0326, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 6.231428571428571e-06, | |
| "loss": 0.0588, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 6.16e-06, | |
| "loss": 0.0802, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 6.088571428571429e-06, | |
| "loss": 0.0913, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 6.017142857142858e-06, | |
| "loss": 0.1228, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.945714285714286e-06, | |
| "loss": 0.119, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.874285714285715e-06, | |
| "loss": 0.1236, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 5.802857142857144e-06, | |
| "loss": 0.1413, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 5.731428571428572e-06, | |
| "loss": 0.1512, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.1980048269033432, | |
| "eval_runtime": 1706.7639, | |
| "eval_samples_per_second": 2.625, | |
| "eval_steps_per_second": 0.082, | |
| "eval_wer": 11.263186751820001, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 5.66e-06, | |
| "loss": 0.1528, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 5.588571428571429e-06, | |
| "loss": 0.1917, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 5.517142857142857e-06, | |
| "loss": 0.2796, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 5.445714285714286e-06, | |
| "loss": 0.2391, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 5.374285714285715e-06, | |
| "loss": 0.2025, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 5.3028571428571425e-06, | |
| "loss": 0.1377, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 5.2314285714285716e-06, | |
| "loss": 0.1342, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 5.1600000000000006e-06, | |
| "loss": 0.1284, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 5.08857142857143e-06, | |
| "loss": 0.1275, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 5.017142857142857e-06, | |
| "loss": 0.1113, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.945714285714286e-06, | |
| "loss": 0.0745, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.874285714285715e-06, | |
| "loss": 0.0842, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.802857142857143e-06, | |
| "loss": 0.1308, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.731428571428572e-06, | |
| "loss": 0.1669, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.66e-06, | |
| "loss": 0.1911, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.588571428571429e-06, | |
| "loss": 0.1787, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.5171428571428575e-06, | |
| "loss": 0.2368, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.445714285714286e-06, | |
| "loss": 0.1796, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.374285714285715e-06, | |
| "loss": 0.1194, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.302857142857143e-06, | |
| "loss": 0.1527, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.1915724277496338, | |
| "eval_runtime": 1733.4878, | |
| "eval_samples_per_second": 2.584, | |
| "eval_steps_per_second": 0.081, | |
| "eval_wer": 10.846896607742996, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.231428571428572e-06, | |
| "loss": 0.1488, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.16e-06, | |
| "loss": 0.1485, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.088571428571429e-06, | |
| "loss": 0.1154, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.017142857142857e-06, | |
| "loss": 0.1026, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.945714285714286e-06, | |
| "loss": 0.1128, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.874285714285715e-06, | |
| "loss": 0.2235, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.802857142857143e-06, | |
| "loss": 0.3356, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.731428571428572e-06, | |
| "loss": 0.3351, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.66e-06, | |
| "loss": 0.2546, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.588571428571429e-06, | |
| "loss": 0.1517, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.5171428571428573e-06, | |
| "loss": 0.1087, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.4457142857142863e-06, | |
| "loss": 0.0966, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.3742857142857145e-06, | |
| "loss": 0.1031, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.302857142857143e-06, | |
| "loss": 0.0992, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.2314285714285716e-06, | |
| "loss": 0.0913, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.1600000000000002e-06, | |
| "loss": 0.1051, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.0885714285714284e-06, | |
| "loss": 0.102, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.0171428571428574e-06, | |
| "loss": 0.0885, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.945714285714286e-06, | |
| "loss": 0.063, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.8742857142857146e-06, | |
| "loss": 0.0918, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.1890150010585785, | |
| "eval_runtime": 1728.8601, | |
| "eval_samples_per_second": 2.591, | |
| "eval_steps_per_second": 0.081, | |
| "eval_wer": 9.649808608067906, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.802857142857143e-06, | |
| "loss": 0.116, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7314285714285714e-06, | |
| "loss": 0.1168, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.6600000000000004e-06, | |
| "loss": 0.1147, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.5885714285714285e-06, | |
| "loss": 0.033, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5171428571428575e-06, | |
| "loss": 0.014, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.445714285714286e-06, | |
| "loss": 0.0493, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.3742857142857147e-06, | |
| "loss": 0.0763, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.302857142857143e-06, | |
| "loss": 0.0583, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.2314285714285715e-06, | |
| "loss": 0.0483, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.16e-06, | |
| "loss": 0.0386, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.0885714285714287e-06, | |
| "loss": 0.0472, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.0171428571428573e-06, | |
| "loss": 0.0519, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.945714285714286e-06, | |
| "loss": 0.0701, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.8742857142857142e-06, | |
| "loss": 0.0581, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.8028571428571432e-06, | |
| "loss": 0.0485, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7314285714285716e-06, | |
| "loss": 0.0431, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.6600000000000002e-06, | |
| "loss": 0.0569, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5885714285714288e-06, | |
| "loss": 0.0906, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5171428571428574e-06, | |
| "loss": 0.069, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.4457142857142858e-06, | |
| "loss": 0.047, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.20336349308490753, | |
| "eval_runtime": 1725.5815, | |
| "eval_samples_per_second": 2.596, | |
| "eval_steps_per_second": 0.081, | |
| "eval_wer": 9.427448750621897, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.3742857142857143e-06, | |
| "loss": 0.0271, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.302857142857143e-06, | |
| "loss": 0.0164, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.2314285714285715e-06, | |
| "loss": 0.036, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.1600000000000001e-06, | |
| "loss": 0.0201, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.0885714285714287e-06, | |
| "loss": 0.0334, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.0171428571428573e-06, | |
| "loss": 0.0561, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.457142857142858e-07, | |
| "loss": 0.0577, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.742857142857144e-07, | |
| "loss": 0.0606, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.028571428571429e-07, | |
| "loss": 0.071, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 7.314285714285715e-07, | |
| "loss": 0.0644, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.6e-07, | |
| "loss": 0.0576, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.885714285714286e-07, | |
| "loss": 0.052, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.171428571428572e-07, | |
| "loss": 0.0633, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 4.457142857142858e-07, | |
| "loss": 0.0583, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.7428571428571434e-07, | |
| "loss": 0.0635, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.028571428571429e-07, | |
| "loss": 0.0828, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.3142857142857144e-07, | |
| "loss": 0.0765, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.6e-07, | |
| "loss": 0.0596, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.857142857142858e-08, | |
| "loss": 0.0581, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.7142857142857143e-08, | |
| "loss": 0.0822, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.19694200158119202, | |
| "eval_runtime": 1711.536, | |
| "eval_samples_per_second": 2.618, | |
| "eval_steps_per_second": 0.082, | |
| "eval_wer": 9.396988496177238, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "step": 4000, | |
| "total_flos": 1.358319892267008e+20, | |
| "train_loss": 0.19088249330222606, | |
| "train_runtime": 43144.9916, | |
| "train_samples_per_second": 1.483, | |
| "train_steps_per_second": 0.093 | |
| } | |
| ], | |
| "max_steps": 4000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.358319892267008e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |