| { | |
| "best_metric": 7.053501375825063, | |
| "best_model_checkpoint": "./tarteel-ai/whisper-tiny-ar-quran/checkpoint-5000", | |
| "epoch": 0.46689700252124383, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.4144, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.2e-06, | |
| "loss": 0.9448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.42e-05, | |
| "loss": 0.6263, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.5066, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.4200000000000002e-05, | |
| "loss": 0.4222, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.9199999999999998e-05, | |
| "loss": 0.3653, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.4200000000000005e-05, | |
| "loss": 0.3186, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 0.2943, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.4200000000000004e-05, | |
| "loss": 0.2975, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.92e-05, | |
| "loss": 0.2573, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.420000000000001e-05, | |
| "loss": 0.2324, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.92e-05, | |
| "loss": 0.2285, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.42e-05, | |
| "loss": 0.2059, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.92e-05, | |
| "loss": 0.2117, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.42e-05, | |
| "loss": 0.2028, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.920000000000001e-05, | |
| "loss": 0.1899, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.42e-05, | |
| "loss": 0.185, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.92e-05, | |
| "loss": 0.1798, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.42e-05, | |
| "loss": 0.1956, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.92e-05, | |
| "loss": 0.1766, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.28293487429618835, | |
| "eval_runtime": 3880.538, | |
| "eval_samples_per_second": 6.038, | |
| "eval_steps_per_second": 0.755, | |
| "eval_wer": 20.023608772394585, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.953333333333333e-05, | |
| "loss": 0.1961, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.897777777777778e-05, | |
| "loss": 0.1728, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.842222222222223e-05, | |
| "loss": 0.165, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.786666666666667e-05, | |
| "loss": 0.1759, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.731111111111112e-05, | |
| "loss": 0.1536, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.675555555555556e-05, | |
| "loss": 0.1539, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.620000000000001e-05, | |
| "loss": 0.1386, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.564444444444444e-05, | |
| "loss": 0.1453, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.50888888888889e-05, | |
| "loss": 0.1326, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.453333333333335e-05, | |
| "loss": 0.135, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.397777777777778e-05, | |
| "loss": 0.1326, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.342222222222222e-05, | |
| "loss": 0.1375, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.286666666666667e-05, | |
| "loss": 0.1172, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.231111111111112e-05, | |
| "loss": 0.119, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.175555555555556e-05, | |
| "loss": 0.1234, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.120000000000001e-05, | |
| "loss": 0.1236, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.064444444444446e-05, | |
| "loss": 0.1089, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.00888888888889e-05, | |
| "loss": 0.1113, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.953333333333333e-05, | |
| "loss": 0.1071, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.897777777777778e-05, | |
| "loss": 0.1129, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.19805501401424408, | |
| "eval_runtime": 4190.8903, | |
| "eval_samples_per_second": 5.591, | |
| "eval_steps_per_second": 0.699, | |
| "eval_wer": 13.836405214229815, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.842222222222223e-05, | |
| "loss": 0.106, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.786666666666667e-05, | |
| "loss": 0.1021, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.731111111111111e-05, | |
| "loss": 0.0947, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.675555555555556e-05, | |
| "loss": 0.1006, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.620000000000001e-05, | |
| "loss": 0.0929, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.564444444444445e-05, | |
| "loss": 0.0935, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.50888888888889e-05, | |
| "loss": 0.0917, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.453333333333335e-05, | |
| "loss": 0.0924, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.397777777777778e-05, | |
| "loss": 0.0959, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.342222222222222e-05, | |
| "loss": 0.0925, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.286666666666667e-05, | |
| "loss": 0.0941, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.231111111111112e-05, | |
| "loss": 0.0846, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.175555555555556e-05, | |
| "loss": 0.0855, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.120000000000001e-05, | |
| "loss": 0.0795, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.064444444444445e-05, | |
| "loss": 0.0804, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.00888888888889e-05, | |
| "loss": 0.0785, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.953333333333333e-05, | |
| "loss": 0.0762, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.897777777777778e-05, | |
| "loss": 0.076, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.842222222222223e-05, | |
| "loss": 0.0765, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.786666666666667e-05, | |
| "loss": 0.0775, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.17625215649604797, | |
| "eval_runtime": 4016.8507, | |
| "eval_samples_per_second": 5.833, | |
| "eval_steps_per_second": 0.729, | |
| "eval_wer": 12.545027694125313, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.731111111111111e-05, | |
| "loss": 0.0688, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.675555555555556e-05, | |
| "loss": 0.0702, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.620000000000001e-05, | |
| "loss": 0.0678, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.564444444444445e-05, | |
| "loss": 0.0735, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.50888888888889e-05, | |
| "loss": 0.0685, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.453333333333333e-05, | |
| "loss": 0.0658, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.397777777777778e-05, | |
| "loss": 0.0698, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.342222222222222e-05, | |
| "loss": 0.0687, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.286666666666667e-05, | |
| "loss": 0.0705, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.231111111111112e-05, | |
| "loss": 0.0631, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.175555555555556e-05, | |
| "loss": 0.0664, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.12e-05, | |
| "loss": 0.0559, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.064444444444445e-05, | |
| "loss": 0.067, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.00888888888889e-05, | |
| "loss": 0.0623, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.953333333333333e-05, | |
| "loss": 0.0571, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.897777777777778e-05, | |
| "loss": 0.066, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.842222222222222e-05, | |
| "loss": 0.0642, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.786666666666667e-05, | |
| "loss": 0.0547, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.731111111111111e-05, | |
| "loss": 0.0496, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.675555555555556e-05, | |
| "loss": 0.0678, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.1484592705965042, | |
| "eval_runtime": 4050.7219, | |
| "eval_samples_per_second": 5.784, | |
| "eval_steps_per_second": 0.723, | |
| "eval_wer": 10.730217503174396, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.620000000000001e-05, | |
| "loss": 0.0489, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.564444444444445e-05, | |
| "loss": 0.0649, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.508888888888888e-05, | |
| "loss": 0.0558, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.453333333333333e-05, | |
| "loss": 0.0512, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.397777777777778e-05, | |
| "loss": 0.0454, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.342222222222222e-05, | |
| "loss": 0.053, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.286666666666667e-05, | |
| "loss": 0.0518, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.231111111111111e-05, | |
| "loss": 0.0592, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.175555555555556e-05, | |
| "loss": 0.0508, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.12e-05, | |
| "loss": 0.0498, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.064444444444445e-05, | |
| "loss": 0.0466, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.00888888888889e-05, | |
| "loss": 0.0455, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.953333333333334e-05, | |
| "loss": 0.0446, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.897777777777778e-05, | |
| "loss": 0.0522, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.842222222222222e-05, | |
| "loss": 0.0487, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.7866666666666666e-05, | |
| "loss": 0.0469, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.7311111111111117e-05, | |
| "loss": 0.039, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.675555555555556e-05, | |
| "loss": 0.0403, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.620000000000001e-05, | |
| "loss": 0.0446, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.564444444444444e-05, | |
| "loss": 0.0437, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.1335567831993103, | |
| "eval_runtime": 4040.5661, | |
| "eval_samples_per_second": 5.799, | |
| "eval_steps_per_second": 0.725, | |
| "eval_wer": 9.669345237188994, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5.508888888888889e-05, | |
| "loss": 0.0459, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5.4533333333333335e-05, | |
| "loss": 0.0483, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5.3977777777777786e-05, | |
| "loss": 0.0423, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5.342222222222223e-05, | |
| "loss": 0.0403, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5.2866666666666666e-05, | |
| "loss": 0.0469, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5.231111111111111e-05, | |
| "loss": 0.0447, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5.1755555555555554e-05, | |
| "loss": 0.0368, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5.1200000000000004e-05, | |
| "loss": 0.043, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5.064444444444445e-05, | |
| "loss": 0.0371, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.00888888888889e-05, | |
| "loss": 0.0362, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.9533333333333336e-05, | |
| "loss": 0.0366, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.897777777777778e-05, | |
| "loss": 0.0388, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.842222222222222e-05, | |
| "loss": 0.0409, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.7866666666666674e-05, | |
| "loss": 0.0348, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.731111111111111e-05, | |
| "loss": 0.0403, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.675555555555556e-05, | |
| "loss": 0.0358, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.6200000000000005e-05, | |
| "loss": 0.0366, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.564444444444444e-05, | |
| "loss": 0.0336, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.508888888888889e-05, | |
| "loss": 0.0341, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.4533333333333336e-05, | |
| "loss": 0.0341, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.12444232404232025, | |
| "eval_runtime": 4101.4445, | |
| "eval_samples_per_second": 5.713, | |
| "eval_steps_per_second": 0.714, | |
| "eval_wer": 8.960168570288877, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.397777777777778e-05, | |
| "loss": 0.0361, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.3422222222222224e-05, | |
| "loss": 0.029, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.286666666666667e-05, | |
| "loss": 0.0347, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.231111111111111e-05, | |
| "loss": 0.0354, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.175555555555556e-05, | |
| "loss": 0.0318, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.12e-05, | |
| "loss": 0.0306, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.064444444444445e-05, | |
| "loss": 0.0275, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.008888888888889e-05, | |
| "loss": 0.0338, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.9533333333333337e-05, | |
| "loss": 0.0326, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.897777777777778e-05, | |
| "loss": 0.031, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.8422222222222224e-05, | |
| "loss": 0.0287, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.786666666666667e-05, | |
| "loss": 0.0275, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.731111111111111e-05, | |
| "loss": 0.0296, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.675555555555556e-05, | |
| "loss": 0.0268, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.62e-05, | |
| "loss": 0.0308, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.564444444444445e-05, | |
| "loss": 0.0327, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.5088888888888886e-05, | |
| "loss": 0.0297, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.453333333333334e-05, | |
| "loss": 0.0286, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.397777777777778e-05, | |
| "loss": 0.0256, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.3422222222222224e-05, | |
| "loss": 0.0302, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.10588590055704117, | |
| "eval_runtime": 4049.1889, | |
| "eval_samples_per_second": 5.787, | |
| "eval_steps_per_second": 0.723, | |
| "eval_wer": 8.222369058095241, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.286666666666667e-05, | |
| "loss": 0.0286, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.231111111111111e-05, | |
| "loss": 0.0258, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.1755555555555556e-05, | |
| "loss": 0.0299, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.12e-05, | |
| "loss": 0.0233, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.064444444444445e-05, | |
| "loss": 0.03, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.008888888888889e-05, | |
| "loss": 0.0243, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.9533333333333334e-05, | |
| "loss": 0.0253, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.897777777777778e-05, | |
| "loss": 0.0215, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.842222222222222e-05, | |
| "loss": 0.0219, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.786666666666667e-05, | |
| "loss": 0.0245, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.7311111111111116e-05, | |
| "loss": 0.0227, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.6755555555555556e-05, | |
| "loss": 0.0225, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.6200000000000003e-05, | |
| "loss": 0.0252, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.5644444444444444e-05, | |
| "loss": 0.0221, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.508888888888889e-05, | |
| "loss": 0.0243, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.4533333333333334e-05, | |
| "loss": 0.0171, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.3977777777777778e-05, | |
| "loss": 0.0195, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.3422222222222222e-05, | |
| "loss": 0.0205, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.2866666666666666e-05, | |
| "loss": 0.0228, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.2311111111111113e-05, | |
| "loss": 0.0189, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.10436350852251053, | |
| "eval_runtime": 4018.7179, | |
| "eval_samples_per_second": 5.83, | |
| "eval_steps_per_second": 0.729, | |
| "eval_wer": 7.6902074344288165, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.1755555555555557e-05, | |
| "loss": 0.0204, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.12e-05, | |
| "loss": 0.0251, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.0644444444444447e-05, | |
| "loss": 0.0258, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.008888888888889e-05, | |
| "loss": 0.0201, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.9533333333333335e-05, | |
| "loss": 0.0168, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.897777777777778e-05, | |
| "loss": 0.0184, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.8422222222222222e-05, | |
| "loss": 0.0191, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.7866666666666666e-05, | |
| "loss": 0.0192, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.731111111111111e-05, | |
| "loss": 0.0174, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.6755555555555557e-05, | |
| "loss": 0.019, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.62e-05, | |
| "loss": 0.0152, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.5644444444444444e-05, | |
| "loss": 0.0186, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.5088888888888888e-05, | |
| "loss": 0.0188, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.4533333333333335e-05, | |
| "loss": 0.0163, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.3977777777777779e-05, | |
| "loss": 0.0181, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.3422222222222223e-05, | |
| "loss": 0.0145, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2866666666666668e-05, | |
| "loss": 0.0221, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.2311111111111112e-05, | |
| "loss": 0.0186, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1755555555555556e-05, | |
| "loss": 0.0152, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.0167, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.09660401940345764, | |
| "eval_runtime": 4073.1436, | |
| "eval_samples_per_second": 5.753, | |
| "eval_steps_per_second": 0.719, | |
| "eval_wer": 7.264315736373445, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.0644444444444445e-05, | |
| "loss": 0.012, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.0088888888888889e-05, | |
| "loss": 0.0162, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.533333333333334e-06, | |
| "loss": 0.0134, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 0.0146, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.422222222222223e-06, | |
| "loss": 0.0165, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.866666666666667e-06, | |
| "loss": 0.0157, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.311111111111112e-06, | |
| "loss": 0.0131, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.755555555555555e-06, | |
| "loss": 0.0138, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.2e-06, | |
| "loss": 0.014, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.6444444444444445e-06, | |
| "loss": 0.0183, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.088888888888889e-06, | |
| "loss": 0.0128, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.533333333333334e-06, | |
| "loss": 0.0161, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.977777777777778e-06, | |
| "loss": 0.0132, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.4222222222222224e-06, | |
| "loss": 0.0199, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.8666666666666666e-06, | |
| "loss": 0.0148, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.311111111111111e-06, | |
| "loss": 0.0136, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.7555555555555558e-06, | |
| "loss": 0.0132, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.014, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.444444444444444e-07, | |
| "loss": 0.0176, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 8.88888888888889e-08, | |
| "loss": 0.0151, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.09276291728019714, | |
| "eval_runtime": 4044.3193, | |
| "eval_samples_per_second": 5.794, | |
| "eval_steps_per_second": 0.724, | |
| "eval_wer": 7.053501375825063, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "step": 5000, | |
| "total_flos": 1.9695108096e+18, | |
| "train_loss": 0.0840680416226387, | |
| "train_runtime": 45146.5595, | |
| "train_samples_per_second": 1.772, | |
| "train_steps_per_second": 0.111 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.9695108096e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |