| { | |
| "best_metric": 20.378586217095535, | |
| "best_model_checkpoint": "/content/checkpoint/whisper-small-hi/checkpoint-3000", | |
| "epoch": 4.527813712807244, | |
| "global_step": 3500, | |
| "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": 4.1984, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 3.3699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.42e-06, | |
| "loss": 2.4858, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.4969, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.42e-06, | |
| "loss": 1.1419, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.92e-06, | |
| "loss": 1.0148, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.9297, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.8621, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.712, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.6186, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.4717, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.3114, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.3384, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.2962, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.3173, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.3202, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.3133, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.3045, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.2761, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.3105, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.32677161693573, | |
| "eval_runtime": 1909.0381, | |
| "eval_samples_per_second": 2.655, | |
| "eval_steps_per_second": 0.332, | |
| "eval_wer": 23.903632599284773, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.800000000000001e-07, | |
| "loss": 0.2945, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.800000000000001e-07, | |
| "loss": 0.2947, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.48e-06, | |
| "loss": 0.2997, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.98e-06, | |
| "loss": 0.301, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.4800000000000004e-06, | |
| "loss": 0.2875, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.9800000000000003e-06, | |
| "loss": 0.3012, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.48e-06, | |
| "loss": 0.2679, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.980000000000001e-06, | |
| "loss": 0.2838, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.48e-06, | |
| "loss": 0.2789, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.960000000000001e-06, | |
| "loss": 0.273, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.460000000000001e-06, | |
| "loss": 0.2716, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.9600000000000005e-06, | |
| "loss": 0.1651, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 6.460000000000001e-06, | |
| "loss": 0.1718, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 6.96e-06, | |
| "loss": 0.1631, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.4600000000000006e-06, | |
| "loss": 0.1572, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.960000000000002e-06, | |
| "loss": 0.1742, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.46e-06, | |
| "loss": 0.1899, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.96e-06, | |
| "loss": 0.1787, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.460000000000001e-06, | |
| "loss": 0.1836, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 9.960000000000001e-06, | |
| "loss": 0.1775, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.3070180416107178, | |
| "eval_runtime": 2136.5113, | |
| "eval_samples_per_second": 2.373, | |
| "eval_steps_per_second": 0.297, | |
| "eval_wer": 22.419402543626145, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.934285714285715e-06, | |
| "loss": 0.1974, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.862857142857144e-06, | |
| "loss": 0.1784, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.791428571428571e-06, | |
| "loss": 0.1785, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.72e-06, | |
| "loss": 0.1861, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.648571428571429e-06, | |
| "loss": 0.1808, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9.577142857142858e-06, | |
| "loss": 0.1741, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.505714285714287e-06, | |
| "loss": 0.184, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.434285714285714e-06, | |
| "loss": 0.1962, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.362857142857143e-06, | |
| "loss": 0.1834, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.291428571428572e-06, | |
| "loss": 0.177, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.220000000000002e-06, | |
| "loss": 0.1855, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.148571428571429e-06, | |
| "loss": 0.1675, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.077142857142858e-06, | |
| "loss": 0.1822, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.005714285714287e-06, | |
| "loss": 0.1666, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.934285714285716e-06, | |
| "loss": 0.196, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.862857142857143e-06, | |
| "loss": 0.1843, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.791428571428572e-06, | |
| "loss": 0.1698, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.720000000000001e-06, | |
| "loss": 0.161, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.64857142857143e-06, | |
| "loss": 0.1897, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.577142857142858e-06, | |
| "loss": 0.1658, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.2858450710773468, | |
| "eval_runtime": 1954.9187, | |
| "eval_samples_per_second": 2.593, | |
| "eval_steps_per_second": 0.324, | |
| "eval_wer": 21.284719421365384, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.505714285714287e-06, | |
| "loss": 0.1836, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.434285714285716e-06, | |
| "loss": 0.1407, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.362857142857143e-06, | |
| "loss": 0.067, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.291428571428572e-06, | |
| "loss": 0.0688, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.220000000000001e-06, | |
| "loss": 0.0763, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.148571428571428e-06, | |
| "loss": 0.0751, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.077142857142857e-06, | |
| "loss": 0.0774, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.005714285714286e-06, | |
| "loss": 0.0796, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.934285714285715e-06, | |
| "loss": 0.0671, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.862857142857143e-06, | |
| "loss": 0.0655, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.791428571428572e-06, | |
| "loss": 0.0691, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.72e-06, | |
| "loss": 0.0634, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 7.64857142857143e-06, | |
| "loss": 0.0695, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.577142857142857e-06, | |
| "loss": 0.0704, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.505714285714286e-06, | |
| "loss": 0.0706, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.434285714285715e-06, | |
| "loss": 0.0641, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.362857142857144e-06, | |
| "loss": 0.0683, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.291428571428571e-06, | |
| "loss": 0.0605, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.22e-06, | |
| "loss": 0.0674, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.148571428571429e-06, | |
| "loss": 0.0684, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.29735004901885986, | |
| "eval_runtime": 1980.7436, | |
| "eval_samples_per_second": 2.559, | |
| "eval_steps_per_second": 0.32, | |
| "eval_wer": 20.935172487967517, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.077142857142858e-06, | |
| "loss": 0.0589, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.0057142857142865e-06, | |
| "loss": 0.0665, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 6.934285714285715e-06, | |
| "loss": 0.0688, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.862857142857144e-06, | |
| "loss": 0.0731, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 6.791428571428572e-06, | |
| "loss": 0.0746, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.720000000000001e-06, | |
| "loss": 0.0735, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 6.648571428571429e-06, | |
| "loss": 0.0657, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.577142857142857e-06, | |
| "loss": 0.0674, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 6.505714285714286e-06, | |
| "loss": 0.0649, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 6.434285714285715e-06, | |
| "loss": 0.0653, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.3628571428571426e-06, | |
| "loss": 0.0709, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 6.2914285714285716e-06, | |
| "loss": 0.069, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 6.220000000000001e-06, | |
| "loss": 0.0603, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 6.14857142857143e-06, | |
| "loss": 0.0262, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 6.077142857142858e-06, | |
| "loss": 0.0296, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 6.005714285714286e-06, | |
| "loss": 0.0269, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 5.934285714285715e-06, | |
| "loss": 0.0257, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 5.862857142857143e-06, | |
| "loss": 0.029, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 5.791428571428572e-06, | |
| "loss": 0.0296, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 5.72e-06, | |
| "loss": 0.0291, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.3039323091506958, | |
| "eval_runtime": 2093.4598, | |
| "eval_samples_per_second": 2.421, | |
| "eval_steps_per_second": 0.303, | |
| "eval_wer": 20.74695490844559, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 5.6485714285714285e-06, | |
| "loss": 0.0283, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 5.5771428571428575e-06, | |
| "loss": 0.0274, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5.5057142857142865e-06, | |
| "loss": 0.025, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 5.4342857142857155e-06, | |
| "loss": 0.0235, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 5.362857142857143e-06, | |
| "loss": 0.0315, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 5.291428571428572e-06, | |
| "loss": 0.0252, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 5.220000000000001e-06, | |
| "loss": 0.024, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 5.14857142857143e-06, | |
| "loss": 0.0269, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 5.077142857142857e-06, | |
| "loss": 0.0287, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 5.005714285714286e-06, | |
| "loss": 0.0296, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 4.934285714285715e-06, | |
| "loss": 0.0285, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 4.862857142857143e-06, | |
| "loss": 0.0251, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 4.7914285714285715e-06, | |
| "loss": 0.0278, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 4.7200000000000005e-06, | |
| "loss": 0.0283, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 4.648571428571429e-06, | |
| "loss": 0.0271, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.577142857142858e-06, | |
| "loss": 0.0283, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 4.505714285714286e-06, | |
| "loss": 0.0254, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 4.434285714285715e-06, | |
| "loss": 0.025, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 4.362857142857143e-06, | |
| "loss": 0.0271, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 4.291428571428572e-06, | |
| "loss": 0.0249, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.30298087000846863, | |
| "eval_runtime": 2105.1167, | |
| "eval_samples_per_second": 2.408, | |
| "eval_steps_per_second": 0.301, | |
| "eval_wer": 20.378586217095535, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.22e-06, | |
| "loss": 0.0278, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 4.148571428571429e-06, | |
| "loss": 0.0256, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 4.0771428571428574e-06, | |
| "loss": 0.0317, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.0057142857142864e-06, | |
| "loss": 0.0237, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.934285714285715e-06, | |
| "loss": 0.0144, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 3.862857142857143e-06, | |
| "loss": 0.0102, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 3.7914285714285722e-06, | |
| "loss": 0.0115, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.7200000000000004e-06, | |
| "loss": 0.0094, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 3.648571428571429e-06, | |
| "loss": 0.0096, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.5771428571428576e-06, | |
| "loss": 0.0108, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 3.505714285714286e-06, | |
| "loss": 0.0112, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 3.4342857142857143e-06, | |
| "loss": 0.0112, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 3.3628571428571433e-06, | |
| "loss": 0.0123, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 3.2914285714285715e-06, | |
| "loss": 0.0097, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.2200000000000005e-06, | |
| "loss": 0.0107, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.1485714285714287e-06, | |
| "loss": 0.0105, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.0771428571428573e-06, | |
| "loss": 0.0111, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.005714285714286e-06, | |
| "loss": 0.0083, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.9342857142857144e-06, | |
| "loss": 0.0102, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 2.8628571428571435e-06, | |
| "loss": 0.0138, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_loss": 0.3253466784954071, | |
| "eval_runtime": 2109.3787, | |
| "eval_samples_per_second": 2.403, | |
| "eval_steps_per_second": 0.301, | |
| "eval_wer": 20.483450297114896, | |
| "step": 3500 | |
| } | |
| ], | |
| "max_steps": 4000, | |
| "num_train_epochs": 6, | |
| "total_flos": 1.615154768510976e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |