| { | |
| "best_metric": 23.110834371108343, | |
| "best_model_checkpoint": "/ml_disk/home/saiteja.malyala/projects/whisper/outdir/kn_in/2022-12-08_16-18-24/checkpoint-3500", | |
| "epoch": 48.775757575757574, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.6000000000000004e-07, | |
| "loss": 2.0129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.600000000000001e-07, | |
| "loss": 1.8503, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.46e-06, | |
| "loss": 1.6612, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.9600000000000003e-06, | |
| "loss": 1.2994, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.46e-06, | |
| "loss": 0.8061, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.96e-06, | |
| "loss": 0.5326, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.46e-06, | |
| "loss": 0.4048, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.96e-06, | |
| "loss": 0.3291, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.4600000000000005e-06, | |
| "loss": 0.2936, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.960000000000001e-06, | |
| "loss": 0.2742, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 5.460000000000001e-06, | |
| "loss": 0.2294, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 5.9600000000000005e-06, | |
| "loss": 0.2148, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.460000000000001e-06, | |
| "loss": 0.2013, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 6.96e-06, | |
| "loss": 0.1752, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 7.4600000000000006e-06, | |
| "loss": 0.1587, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 7.960000000000002e-06, | |
| "loss": 0.1406, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 8.46e-06, | |
| "loss": 0.1077, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 8.96e-06, | |
| "loss": 0.0902, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 9.460000000000001e-06, | |
| "loss": 0.0872, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 9.960000000000001e-06, | |
| "loss": 0.0792, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_loss": 0.1414351910352707, | |
| "eval_runtime": 112.7148, | |
| "eval_samples_per_second": 7.275, | |
| "eval_steps_per_second": 0.231, | |
| "eval_wer": 24.70485678704857, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 9.934285714285715e-06, | |
| "loss": 0.0633, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 9.862857142857144e-06, | |
| "loss": 0.0578, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.791428571428571e-06, | |
| "loss": 0.0613, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 9.72e-06, | |
| "loss": 0.0386, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 9.648571428571429e-06, | |
| "loss": 0.0381, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 9.577142857142858e-06, | |
| "loss": 0.0368, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 9.505714285714287e-06, | |
| "loss": 0.0263, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 9.434285714285714e-06, | |
| "loss": 0.0216, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 9.362857142857143e-06, | |
| "loss": 0.0234, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 9.291428571428572e-06, | |
| "loss": 0.0194, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 9.220000000000002e-06, | |
| "loss": 0.0125, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 9.148571428571429e-06, | |
| "loss": 0.0151, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 9.077142857142858e-06, | |
| "loss": 0.0136, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 9.005714285714287e-06, | |
| "loss": 0.0079, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 8.934285714285716e-06, | |
| "loss": 0.008, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 8.862857142857143e-06, | |
| "loss": 0.0105, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 8.791428571428572e-06, | |
| "loss": 0.0058, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 8.720000000000001e-06, | |
| "loss": 0.0062, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 8.64857142857143e-06, | |
| "loss": 0.0061, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 8.577142857142858e-06, | |
| "loss": 0.0067, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "eval_loss": 0.1930890679359436, | |
| "eval_runtime": 107.7523, | |
| "eval_samples_per_second": 7.61, | |
| "eval_steps_per_second": 0.241, | |
| "eval_wer": 23.775840597758403, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 8.505714285714287e-06, | |
| "loss": 0.0043, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 8.434285714285716e-06, | |
| "loss": 0.0052, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 8.362857142857143e-06, | |
| "loss": 0.0033, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 8.291428571428572e-06, | |
| "loss": 0.0036, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 8.220000000000001e-06, | |
| "loss": 0.0033, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 8.148571428571428e-06, | |
| "loss": 0.0038, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 8.077142857142857e-06, | |
| "loss": 0.0028, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 8.005714285714286e-06, | |
| "loss": 0.004, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 7.934285714285715e-06, | |
| "loss": 0.0034, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 7.862857142857143e-06, | |
| "loss": 0.0029, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 7.791428571428572e-06, | |
| "loss": 0.0019, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 7.72e-06, | |
| "loss": 0.002, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 7.64857142857143e-06, | |
| "loss": 0.0017, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 7.577142857142857e-06, | |
| "loss": 0.0019, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 7.505714285714286e-06, | |
| "loss": 0.0017, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "learning_rate": 7.434285714285715e-06, | |
| "loss": 0.0023, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 7.362857142857144e-06, | |
| "loss": 0.0021, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 17.68, | |
| "learning_rate": 7.291428571428571e-06, | |
| "loss": 0.0013, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "learning_rate": 7.22e-06, | |
| "loss": 0.0016, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "learning_rate": 7.148571428571429e-06, | |
| "loss": 0.0011, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "eval_loss": 0.2161669284105301, | |
| "eval_runtime": 105.1782, | |
| "eval_samples_per_second": 7.796, | |
| "eval_steps_per_second": 0.247, | |
| "eval_wer": 23.322540473225406, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 7.077142857142858e-06, | |
| "loss": 0.0013, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 7.0057142857142865e-06, | |
| "loss": 0.0014, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "learning_rate": 6.934285714285715e-06, | |
| "loss": 0.0011, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 19.51, | |
| "learning_rate": 6.862857142857144e-06, | |
| "loss": 0.0012, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 6.791428571428572e-06, | |
| "loss": 0.0009, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "learning_rate": 6.720000000000001e-06, | |
| "loss": 0.0009, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 6.648571428571429e-06, | |
| "loss": 0.0005, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 6.577142857142857e-06, | |
| "loss": 0.0013, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 21.04, | |
| "learning_rate": 6.505714285714286e-06, | |
| "loss": 0.001, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 21.34, | |
| "learning_rate": 6.434285714285715e-06, | |
| "loss": 0.0005, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 6.3628571428571426e-06, | |
| "loss": 0.0007, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 21.95, | |
| "learning_rate": 6.2914285714285716e-06, | |
| "loss": 0.0008, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 22.25, | |
| "learning_rate": 6.220000000000001e-06, | |
| "loss": 0.0009, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 6.14857142857143e-06, | |
| "loss": 0.0006, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 6.077142857142858e-06, | |
| "loss": 0.0005, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "learning_rate": 6.005714285714286e-06, | |
| "loss": 0.0004, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 5.934285714285715e-06, | |
| "loss": 0.0003, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 23.78, | |
| "learning_rate": 5.862857142857143e-06, | |
| "loss": 0.0004, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 24.08, | |
| "learning_rate": 5.791428571428572e-06, | |
| "loss": 0.0003, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 5.72e-06, | |
| "loss": 0.0002, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "eval_loss": 0.22942006587982178, | |
| "eval_runtime": 105.2283, | |
| "eval_samples_per_second": 7.793, | |
| "eval_steps_per_second": 0.247, | |
| "eval_wer": 23.133250311332503, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 24.69, | |
| "learning_rate": 5.6485714285714285e-06, | |
| "loss": 0.0002, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "learning_rate": 5.5771428571428575e-06, | |
| "loss": 0.0002, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 5.5057142857142865e-06, | |
| "loss": 0.0002, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 25.61, | |
| "learning_rate": 5.4342857142857155e-06, | |
| "loss": 0.0001, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "learning_rate": 5.362857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 5.291428571428572e-06, | |
| "loss": 0.0001, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 26.52, | |
| "learning_rate": 5.220000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 5.14857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 27.13, | |
| "learning_rate": 5.077142857142857e-06, | |
| "loss": 0.0001, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 27.44, | |
| "learning_rate": 5.005714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 27.74, | |
| "learning_rate": 4.934285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 28.05, | |
| "learning_rate": 4.862857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 28.35, | |
| "learning_rate": 4.7914285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 28.65, | |
| "learning_rate": 4.7200000000000005e-06, | |
| "loss": 0.0001, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 4.648571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 29.27, | |
| "learning_rate": 4.577142857142858e-06, | |
| "loss": 0.0001, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 4.505714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 29.87, | |
| "learning_rate": 4.434285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 4.362857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 30.48, | |
| "learning_rate": 4.291428571428572e-06, | |
| "loss": 0.0001, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 30.48, | |
| "eval_loss": 0.24061080813407898, | |
| "eval_runtime": 105.1705, | |
| "eval_samples_per_second": 7.797, | |
| "eval_steps_per_second": 0.247, | |
| "eval_wer": 23.16562889165629, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 30.79, | |
| "learning_rate": 4.22e-06, | |
| "loss": 0.0001, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 31.1, | |
| "learning_rate": 4.148571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "learning_rate": 4.0771428571428574e-06, | |
| "loss": 0.0001, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "learning_rate": 4.0057142857142864e-06, | |
| "loss": 0.0001, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.934285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 32.32, | |
| "learning_rate": 3.862857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 32.62, | |
| "learning_rate": 3.7914285714285722e-06, | |
| "loss": 0.0001, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "learning_rate": 3.7200000000000004e-06, | |
| "loss": 0.0001, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 33.23, | |
| "learning_rate": 3.648571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 33.53, | |
| "learning_rate": 3.5771428571428576e-06, | |
| "loss": 0.0001, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 33.84, | |
| "learning_rate": 3.505714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 34.15, | |
| "learning_rate": 3.4342857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 34.45, | |
| "learning_rate": 3.3628571428571433e-06, | |
| "loss": 0.0001, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "learning_rate": 3.2914285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 35.06, | |
| "learning_rate": 3.2200000000000005e-06, | |
| "loss": 0.0001, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 35.36, | |
| "learning_rate": 3.1485714285714287e-06, | |
| "loss": 0.0001, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 35.67, | |
| "learning_rate": 3.0771428571428573e-06, | |
| "loss": 0.0001, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 3.005714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 36.28, | |
| "learning_rate": 2.9342857142857144e-06, | |
| "loss": 0.0001, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 36.58, | |
| "learning_rate": 2.8628571428571435e-06, | |
| "loss": 0.0001, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 36.58, | |
| "eval_loss": 0.24610796570777893, | |
| "eval_runtime": 105.0431, | |
| "eval_samples_per_second": 7.806, | |
| "eval_steps_per_second": 0.248, | |
| "eval_wer": 23.153175591531756, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 36.88, | |
| "learning_rate": 2.7914285714285716e-06, | |
| "loss": 0.0001, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "learning_rate": 2.7200000000000002e-06, | |
| "loss": 0.0001, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 2.648571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 37.8, | |
| "learning_rate": 2.5771428571428574e-06, | |
| "loss": 0.0001, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 38.11, | |
| "learning_rate": 2.5057142857142856e-06, | |
| "loss": 0.0001, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 38.41, | |
| "learning_rate": 2.4342857142857146e-06, | |
| "loss": 0.0001, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 38.72, | |
| "learning_rate": 2.362857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 2.2914285714285718e-06, | |
| "loss": 0.0001, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 39.33, | |
| "learning_rate": 2.2200000000000003e-06, | |
| "loss": 0.0001, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 39.63, | |
| "learning_rate": 2.148571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 39.93, | |
| "learning_rate": 2.077142857142857e-06, | |
| "loss": 0.0001, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 40.24, | |
| "learning_rate": 2.0057142857142857e-06, | |
| "loss": 0.0001, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 1.9342857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "learning_rate": 1.8628571428571429e-06, | |
| "loss": 0.0001, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 41.16, | |
| "learning_rate": 1.7914285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 41.46, | |
| "learning_rate": 1.72e-06, | |
| "loss": 0.0001, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "learning_rate": 1.6485714285714289e-06, | |
| "loss": 0.0001, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 42.07, | |
| "learning_rate": 1.5771428571428574e-06, | |
| "loss": 0.0001, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 42.38, | |
| "learning_rate": 1.5057142857142858e-06, | |
| "loss": 0.0001, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 42.68, | |
| "learning_rate": 1.4342857142857144e-06, | |
| "loss": 0.0001, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 42.68, | |
| "eval_loss": 0.24934539198875427, | |
| "eval_runtime": 105.7821, | |
| "eval_samples_per_second": 7.752, | |
| "eval_steps_per_second": 0.246, | |
| "eval_wer": 23.110834371108343, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 42.98, | |
| "learning_rate": 1.362857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 43.29, | |
| "learning_rate": 1.2914285714285716e-06, | |
| "loss": 0.0001, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 43.59, | |
| "learning_rate": 1.2200000000000002e-06, | |
| "loss": 0.0001, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 43.9, | |
| "learning_rate": 1.1485714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 44.21, | |
| "learning_rate": 1.0771428571428574e-06, | |
| "loss": 0.0001, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 44.51, | |
| "learning_rate": 1.0057142857142857e-06, | |
| "loss": 0.0001, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 44.81, | |
| "learning_rate": 9.342857142857144e-07, | |
| "loss": 0.0001, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 45.12, | |
| "learning_rate": 8.628571428571429e-07, | |
| "loss": 0.0001, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 7.914285714285715e-07, | |
| "loss": 0.0001, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 45.73, | |
| "learning_rate": 7.2e-07, | |
| "loss": 0.0001, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 46.04, | |
| "learning_rate": 6.485714285714287e-07, | |
| "loss": 0.0001, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 46.34, | |
| "learning_rate": 5.771428571428572e-07, | |
| "loss": 0.0001, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 46.64, | |
| "learning_rate": 5.057142857142858e-07, | |
| "loss": 0.0001, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "learning_rate": 4.342857142857143e-07, | |
| "loss": 0.0001, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 47.25, | |
| "learning_rate": 3.6285714285714283e-07, | |
| "loss": 0.0001, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 47.56, | |
| "learning_rate": 2.914285714285715e-07, | |
| "loss": 0.0001, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 47.86, | |
| "learning_rate": 2.2e-07, | |
| "loss": 0.0001, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 48.17, | |
| "learning_rate": 1.4857142857142857e-07, | |
| "loss": 0.0001, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 48.47, | |
| "learning_rate": 7.714285714285715e-08, | |
| "loss": 0.0, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 48.78, | |
| "learning_rate": 5.714285714285715e-09, | |
| "loss": 0.0001, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 48.78, | |
| "eval_loss": 0.2507011592388153, | |
| "eval_runtime": 104.9754, | |
| "eval_samples_per_second": 7.811, | |
| "eval_steps_per_second": 0.248, | |
| "eval_wer": 23.12577833125778, | |
| "step": 4000 | |
| } | |
| ], | |
| "max_steps": 4000, | |
| "num_train_epochs": 49, | |
| "total_flos": 3.7049748266057466e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |