| { | |
| "best_metric": 5.754409897414504, | |
| "best_model_checkpoint": "./tarteel-ai/whisper-base-ar-quran/checkpoint-5000", | |
| "epoch": 3.1966, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.1527, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9e-06, | |
| "loss": 0.4624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.3386, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.2467, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.1953, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.2176, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.1815, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.135, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0715, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.1092, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.19689758121967316, | |
| "eval_runtime": 3129.8332, | |
| "eval_samples_per_second": 7.486, | |
| "eval_steps_per_second": 0.117, | |
| "eval_wer": 13.388995632478606, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0848, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.9e-05, | |
| "loss": 0.056, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0652, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.9e-05, | |
| "loss": 0.089, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.1052, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 0.0804, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.07, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 0.0389, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.038, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.0361, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.1583031862974167, | |
| "eval_runtime": 3321.2758, | |
| "eval_samples_per_second": 7.055, | |
| "eval_steps_per_second": 0.11, | |
| "eval_wer": 10.637548504050336, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.955555555555556e-05, | |
| "loss": 0.022, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.0211, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.844444444444444e-05, | |
| "loss": 0.0484, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.78888888888889e-05, | |
| "loss": 0.0241, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.733333333333335e-05, | |
| "loss": 0.0224, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.677777777777778e-05, | |
| "loss": 0.0272, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.622222222222222e-05, | |
| "loss": 0.0322, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.566666666666667e-05, | |
| "loss": 0.029, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.511111111111112e-05, | |
| "loss": 0.0244, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.455555555555556e-05, | |
| "loss": 0.0192, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.11088771373033524, | |
| "eval_runtime": 3203.8487, | |
| "eval_samples_per_second": 7.313, | |
| "eval_steps_per_second": 0.115, | |
| "eval_wer": 8.846793683080142, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.034, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.344444444444444e-05, | |
| "loss": 0.0251, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.28888888888889e-05, | |
| "loss": 0.037, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.233333333333333e-05, | |
| "loss": 0.0162, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.177777777777778e-05, | |
| "loss": 0.0219, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.122222222222223e-05, | |
| "loss": 0.0346, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.066666666666667e-05, | |
| "loss": 0.0228, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.011111111111111e-05, | |
| "loss": 0.016, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.955555555555556e-05, | |
| "loss": 0.0186, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 0.0144, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.11568614840507507, | |
| "eval_runtime": 3153.953, | |
| "eval_samples_per_second": 7.429, | |
| "eval_steps_per_second": 0.116, | |
| "eval_wer": 7.9754208928500745, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.844444444444445e-05, | |
| "loss": 0.0093, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.78888888888889e-05, | |
| "loss": 0.0218, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.733333333333333e-05, | |
| "loss": 0.016, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.677777777777778e-05, | |
| "loss": 0.0149, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.622222222222222e-05, | |
| "loss": 0.0122, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.566666666666667e-05, | |
| "loss": 0.0078, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.511111111111112e-05, | |
| "loss": 0.0087, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.455555555555556e-05, | |
| "loss": 0.0065, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0059, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.344444444444445e-05, | |
| "loss": 0.008, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.09997964650392532, | |
| "eval_runtime": 3103.3278, | |
| "eval_samples_per_second": 7.55, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 7.536029767759106, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.28888888888889e-05, | |
| "loss": 0.0087, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.233333333333333e-05, | |
| "loss": 0.0096, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.177777777777778e-05, | |
| "loss": 0.0088, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.122222222222222e-05, | |
| "loss": 0.0115, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 8.066666666666667e-05, | |
| "loss": 0.0114, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 8.011111111111111e-05, | |
| "loss": 0.0038, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.955555555555556e-05, | |
| "loss": 0.0106, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 0.0075, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.844444444444446e-05, | |
| "loss": 0.0094, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.788888888888888e-05, | |
| "loss": 0.0048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.09334036707878113, | |
| "eval_runtime": 3157.6907, | |
| "eval_samples_per_second": 7.42, | |
| "eval_steps_per_second": 0.116, | |
| "eval_wer": 6.822691623351776, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.733333333333333e-05, | |
| "loss": 0.0034, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.677777777777778e-05, | |
| "loss": 0.003, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.622222222222223e-05, | |
| "loss": 0.005, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.566666666666667e-05, | |
| "loss": 0.0043, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.511111111111111e-05, | |
| "loss": 0.0027, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.455555555555556e-05, | |
| "loss": 0.0213, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0122, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.344444444444445e-05, | |
| "loss": 0.006, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.28888888888889e-05, | |
| "loss": 0.0123, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.233333333333335e-05, | |
| "loss": 0.0113, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.09547463804483414, | |
| "eval_runtime": 3101.8736, | |
| "eval_samples_per_second": 7.554, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 6.963775860791473, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.177777777777777e-05, | |
| "loss": 0.0087, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.122222222222222e-05, | |
| "loss": 0.0088, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.066666666666667e-05, | |
| "loss": 0.0112, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.011111111111112e-05, | |
| "loss": 0.008, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.955555555555556e-05, | |
| "loss": 0.0044, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.9e-05, | |
| "loss": 0.0143, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.844444444444445e-05, | |
| "loss": 0.0123, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.788888888888888e-05, | |
| "loss": 0.0042, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.733333333333333e-05, | |
| "loss": 0.0029, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.677777777777779e-05, | |
| "loss": 0.0209, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.08239686489105225, | |
| "eval_runtime": 3082.9101, | |
| "eval_samples_per_second": 7.6, | |
| "eval_steps_per_second": 0.119, | |
| "eval_wer": 6.358636131571709, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.622222222222224e-05, | |
| "loss": 0.0126, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.566666666666666e-05, | |
| "loss": 0.0181, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.511111111111111e-05, | |
| "loss": 0.0067, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.455555555555556e-05, | |
| "loss": 0.0049, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0085, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.344444444444445e-05, | |
| "loss": 0.0071, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.28888888888889e-05, | |
| "loss": 0.0051, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.233333333333334e-05, | |
| "loss": 0.0241, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.177777777777779e-05, | |
| "loss": 0.0056, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.122222222222222e-05, | |
| "loss": 0.0043, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 0.08303235471248627, | |
| "eval_runtime": 3099.7955, | |
| "eval_samples_per_second": 7.559, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 6.344426208376344, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.066666666666667e-05, | |
| "loss": 0.0036, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.011111111111112e-05, | |
| "loss": 0.0092, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 5.9555555555555554e-05, | |
| "loss": 0.0048, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 5.9e-05, | |
| "loss": 0.0054, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 5.844444444444445e-05, | |
| "loss": 0.0044, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 5.788888888888889e-05, | |
| "loss": 0.0036, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 5.7333333333333336e-05, | |
| "loss": 0.004, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 5.6777777777777786e-05, | |
| "loss": 0.0059, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 5.622222222222222e-05, | |
| "loss": 0.005, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 5.566666666666667e-05, | |
| "loss": 0.002, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.10149681568145752, | |
| "eval_runtime": 3102.277, | |
| "eval_samples_per_second": 7.553, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 6.302506934950017, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 5.511111111111111e-05, | |
| "loss": 0.005, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 5.455555555555556e-05, | |
| "loss": 0.0027, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0041, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5.3444444444444455e-05, | |
| "loss": 0.0042, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 5.2888888888888885e-05, | |
| "loss": 0.0061, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 5.2333333333333336e-05, | |
| "loss": 0.0047, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 5.177777777777778e-05, | |
| "loss": 0.0026, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.122222222222223e-05, | |
| "loss": 0.0023, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.0666666666666674e-05, | |
| "loss": 0.0018, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.011111111111111e-05, | |
| "loss": 0.0013, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.08628152310848236, | |
| "eval_runtime": 3108.0423, | |
| "eval_samples_per_second": 7.539, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 6.063881724719278, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.955555555555556e-05, | |
| "loss": 0.0019, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.0021, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.844444444444445e-05, | |
| "loss": 0.0008, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.7888888888888886e-05, | |
| "loss": 0.0014, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.7333333333333336e-05, | |
| "loss": 0.0007, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.677777777777778e-05, | |
| "loss": 0.0008, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.6222222222222224e-05, | |
| "loss": 0.0027, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.566666666666667e-05, | |
| "loss": 0.0023, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.511111111111112e-05, | |
| "loss": 0.0012, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.4555555555555555e-05, | |
| "loss": 0.0014, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.09052816778421402, | |
| "eval_runtime": 3089.8491, | |
| "eval_samples_per_second": 7.583, | |
| "eval_steps_per_second": 0.119, | |
| "eval_wer": 6.021251955133183, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0012, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.344444444444445e-05, | |
| "loss": 0.0013, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.2888888888888886e-05, | |
| "loss": 0.0021, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.233333333333334e-05, | |
| "loss": 0.0024, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.177777777777778e-05, | |
| "loss": 0.0016, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.1222222222222224e-05, | |
| "loss": 0.0008, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.066666666666667e-05, | |
| "loss": 0.0013, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.011111111111111e-05, | |
| "loss": 0.0025, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.9555555555555556e-05, | |
| "loss": 0.0064, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.0018, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.08641628921031952, | |
| "eval_runtime": 3083.8255, | |
| "eval_samples_per_second": 7.598, | |
| "eval_steps_per_second": 0.119, | |
| "eval_wer": 6.029270411793424, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.844444444444444e-05, | |
| "loss": 0.0021, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.7888888888888894e-05, | |
| "loss": 0.0011, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.733333333333334e-05, | |
| "loss": 0.0021, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.677777777777778e-05, | |
| "loss": 0.0071, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.6222222222222225e-05, | |
| "loss": 0.0017, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.566666666666667e-05, | |
| "loss": 0.0016, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.511111111111111e-05, | |
| "loss": 0.0005, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.4555555555555556e-05, | |
| "loss": 0.0024, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0024, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.3444444444444443e-05, | |
| "loss": 0.0008, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.0887165442109108, | |
| "eval_runtime": 3111.2967, | |
| "eval_samples_per_second": 7.531, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 5.930815943939823, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 3.2888888888888894e-05, | |
| "loss": 0.0013, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 3.233333333333333e-05, | |
| "loss": 0.0009, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.177777777777778e-05, | |
| "loss": 0.0012, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.1222222222222225e-05, | |
| "loss": 0.0012, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.066666666666667e-05, | |
| "loss": 0.0007, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.0111111111111113e-05, | |
| "loss": 0.0046, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.955555555555556e-05, | |
| "loss": 0.0016, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0007, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.8444444444444447e-05, | |
| "loss": 0.0018, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.788888888888889e-05, | |
| "loss": 0.0029, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.07773207873106003, | |
| "eval_runtime": 3114.8324, | |
| "eval_samples_per_second": 7.522, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 5.915895524584689, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.733333333333333e-05, | |
| "loss": 0.0026, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.677777777777778e-05, | |
| "loss": 0.002, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2.6222222222222226e-05, | |
| "loss": 0.0025, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2.5666666666666666e-05, | |
| "loss": 0.001, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.5111111111111113e-05, | |
| "loss": 0.0004, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.4555555555555557e-05, | |
| "loss": 0.0021, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0006, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.3444444444444448e-05, | |
| "loss": 0.001, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.288888888888889e-05, | |
| "loss": 0.0013, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.2333333333333335e-05, | |
| "loss": 0.0022, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.08468455821275711, | |
| "eval_runtime": 3072.4642, | |
| "eval_samples_per_second": 7.626, | |
| "eval_steps_per_second": 0.119, | |
| "eval_wer": 5.874889746220922, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.177777777777778e-05, | |
| "loss": 0.0018, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.1222222222222223e-05, | |
| "loss": 0.0008, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.0666666666666666e-05, | |
| "loss": 0.0013, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2.011111111111111e-05, | |
| "loss": 0.0003, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.9555555555555557e-05, | |
| "loss": 0.0006, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0006, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.8444444444444445e-05, | |
| "loss": 0.0004, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.788888888888889e-05, | |
| "loss": 0.0002, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.7333333333333336e-05, | |
| "loss": 0.0001, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.677777777777778e-05, | |
| "loss": 0.0005, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.08272121101617813, | |
| "eval_runtime": 3097.4968, | |
| "eval_samples_per_second": 7.564, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 5.835203460725294, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.6222222222222223e-05, | |
| "loss": 0.0013, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.5666666666666667e-05, | |
| "loss": 0.0007, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.5111111111111112e-05, | |
| "loss": 0.0006, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.4555555555555556e-05, | |
| "loss": 0.0003, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0002, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.3444444444444445e-05, | |
| "loss": 0.0016, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.2888888888888889e-05, | |
| "loss": 0.0004, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.2333333333333334e-05, | |
| "loss": 0.0003, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.1777777777777778e-05, | |
| "loss": 0.0003, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.1222222222222224e-05, | |
| "loss": 0.0003, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 0.08255437761545181, | |
| "eval_runtime": 3117.117, | |
| "eval_samples_per_second": 7.517, | |
| "eval_steps_per_second": 0.118, | |
| "eval_wer": 5.779987759166161, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.0111111111111111e-05, | |
| "loss": 0.0002, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.0001, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0003, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.0005, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.88888888888889e-06, | |
| "loss": 0.0005, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.333333333333334e-06, | |
| "loss": 0.0008, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 6.777777777777779e-06, | |
| "loss": 0.0005, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 6.222222222222222e-06, | |
| "loss": 0.0004, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.666666666666667e-06, | |
| "loss": 0.0006, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 0.08329758793115616, | |
| "eval_runtime": 3126.9679, | |
| "eval_samples_per_second": 7.493, | |
| "eval_steps_per_second": 0.117, | |
| "eval_wer": 5.762529853526142, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 0.0002, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.555555555555556e-06, | |
| "loss": 0.0003, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0004, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.4444444444444444e-06, | |
| "loss": 0.0001, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.888888888888889e-06, | |
| "loss": 0.0002, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2.3333333333333336e-06, | |
| "loss": 0.0006, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.0004, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.2222222222222223e-06, | |
| "loss": 0.0001, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.0005, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.1111111111111112e-07, | |
| "loss": 0.0003, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.08391360193490982, | |
| "eval_runtime": 3124.2207, | |
| "eval_samples_per_second": 7.5, | |
| "eval_steps_per_second": 0.117, | |
| "eval_wer": 5.754409897414504, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "step": 5000, | |
| "total_flos": 4.151039849534587e+19, | |
| "train_loss": 0.024749002781091257, | |
| "train_runtime": 101889.8071, | |
| "train_samples_per_second": 6.281, | |
| "train_steps_per_second": 0.049 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 4.151039849534587e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |