|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.1946666666666665, |
|
"global_step": 3000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.4e-07, |
|
"loss": 1.1445, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9.400000000000001e-07, |
|
"loss": 0.8079, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.44e-06, |
|
"loss": 0.3846, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.94e-06, |
|
"loss": 0.2454, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.4400000000000004e-06, |
|
"loss": 0.2174, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.9400000000000002e-06, |
|
"loss": 0.2138, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.44e-06, |
|
"loss": 0.1577, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.94e-06, |
|
"loss": 0.1403, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.440000000000001e-06, |
|
"loss": 0.1502, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.94e-06, |
|
"loss": 0.1715, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 5.4400000000000004e-06, |
|
"loss": 0.211, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 5.94e-06, |
|
"loss": 0.2042, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 6.440000000000001e-06, |
|
"loss": 0.1717, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 6.9400000000000005e-06, |
|
"loss": 0.1673, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 7.440000000000001e-06, |
|
"loss": 0.1695, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 7.94e-06, |
|
"loss": 0.1467, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 8.44e-06, |
|
"loss": 0.1386, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 8.94e-06, |
|
"loss": 0.1342, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 9.440000000000001e-06, |
|
"loss": 0.1279, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.940000000000001e-06, |
|
"loss": 0.1733, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.912000000000001e-06, |
|
"loss": 0.1542, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 9.812e-06, |
|
"loss": 0.1655, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 9.712e-06, |
|
"loss": 0.1478, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.612000000000002e-06, |
|
"loss": 0.1491, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 9.512000000000001e-06, |
|
"loss": 0.122, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 9.412e-06, |
|
"loss": 0.1205, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 9.312000000000002e-06, |
|
"loss": 0.1172, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 9.212000000000001e-06, |
|
"loss": 0.098, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 9.112e-06, |
|
"loss": 0.1155, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 9.012000000000001e-06, |
|
"loss": 0.1216, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 8.912e-06, |
|
"loss": 0.1465, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 8.812000000000001e-06, |
|
"loss": 0.1488, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 8.712e-06, |
|
"loss": 0.1468, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 8.612e-06, |
|
"loss": 0.1477, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 8.512e-06, |
|
"loss": 0.1332, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 8.412e-06, |
|
"loss": 0.1738, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 8.312000000000001e-06, |
|
"loss": 0.1218, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 8.212e-06, |
|
"loss": 0.159, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 8.112000000000001e-06, |
|
"loss": 0.1608, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 8.012e-06, |
|
"loss": 0.1187, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"eval_loss": 0.21685300767421722, |
|
"eval_runtime": 5878.194, |
|
"eval_samples_per_second": 1.726, |
|
"eval_steps_per_second": 0.108, |
|
"eval_wer": 13.767840874582449, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 7.912000000000001e-06, |
|
"loss": 0.109, |
|
"step": 1025 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 7.812e-06, |
|
"loss": 0.1401, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 7.712e-06, |
|
"loss": 0.1404, |
|
"step": 1075 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 7.612e-06, |
|
"loss": 0.1599, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 7.512e-06, |
|
"loss": 0.1272, |
|
"step": 1125 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 7.412e-06, |
|
"loss": 0.1656, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 7.3120000000000005e-06, |
|
"loss": 0.2091, |
|
"step": 1175 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 7.212e-06, |
|
"loss": 0.189, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 7.1120000000000015e-06, |
|
"loss": 0.1123, |
|
"step": 1225 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 7.012000000000001e-06, |
|
"loss": 0.076, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 6.912000000000001e-06, |
|
"loss": 0.0799, |
|
"step": 1275 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 6.812000000000001e-06, |
|
"loss": 0.0715, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 6.712000000000001e-06, |
|
"loss": 0.0979, |
|
"step": 1325 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 6.612e-06, |
|
"loss": 0.1215, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 6.5120000000000005e-06, |
|
"loss": 0.0933, |
|
"step": 1375 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 6.412000000000001e-06, |
|
"loss": 0.0688, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 6.312000000000001e-06, |
|
"loss": 0.0642, |
|
"step": 1425 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 6.212e-06, |
|
"loss": 0.0744, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 6.112e-06, |
|
"loss": 0.0572, |
|
"step": 1475 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 6.012e-06, |
|
"loss": 0.0602, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 5.912e-06, |
|
"loss": 0.0528, |
|
"step": 1525 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 5.812000000000001e-06, |
|
"loss": 0.0747, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 5.7120000000000005e-06, |
|
"loss": 0.0908, |
|
"step": 1575 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 5.612000000000001e-06, |
|
"loss": 0.0745, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 5.512000000000001e-06, |
|
"loss": 0.0652, |
|
"step": 1625 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 5.412000000000001e-06, |
|
"loss": 0.0629, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 5.312e-06, |
|
"loss": 0.0595, |
|
"step": 1675 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 5.212e-06, |
|
"loss": 0.0544, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 5.112e-06, |
|
"loss": 0.0589, |
|
"step": 1725 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 5.0120000000000005e-06, |
|
"loss": 0.0611, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 4.9120000000000006e-06, |
|
"loss": 0.0592, |
|
"step": 1775 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.812000000000001e-06, |
|
"loss": 0.0612, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 4.712000000000001e-06, |
|
"loss": 0.0774, |
|
"step": 1825 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 4.612e-06, |
|
"loss": 0.0962, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 4.512e-06, |
|
"loss": 0.1123, |
|
"step": 1875 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 4.412e-06, |
|
"loss": 0.103, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 4.312e-06, |
|
"loss": 0.0872, |
|
"step": 1925 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 4.2120000000000005e-06, |
|
"loss": 0.0847, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.112000000000001e-06, |
|
"loss": 0.0736, |
|
"step": 1975 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.012000000000001e-06, |
|
"loss": 0.0579, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"eval_loss": 0.1813589185476303, |
|
"eval_runtime": 5892.9893, |
|
"eval_samples_per_second": 1.721, |
|
"eval_steps_per_second": 0.108, |
|
"eval_wer": 10.82219860309748, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 3.912e-06, |
|
"loss": 0.0503, |
|
"step": 2025 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.812e-06, |
|
"loss": 0.0596, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 3.712e-06, |
|
"loss": 0.0607, |
|
"step": 2075 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 3.6120000000000003e-06, |
|
"loss": 0.0701, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 3.5120000000000004e-06, |
|
"loss": 0.0631, |
|
"step": 2125 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 3.412e-06, |
|
"loss": 0.0537, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 3.3120000000000002e-06, |
|
"loss": 0.0419, |
|
"step": 2175 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 3.212e-06, |
|
"loss": 0.0759, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 3.112e-06, |
|
"loss": 0.1213, |
|
"step": 2225 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 3.0120000000000006e-06, |
|
"loss": 0.1049, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 2.9120000000000002e-06, |
|
"loss": 0.062, |
|
"step": 2275 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 2.8120000000000004e-06, |
|
"loss": 0.0587, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 2.712e-06, |
|
"loss": 0.0745, |
|
"step": 2325 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 2.612e-06, |
|
"loss": 0.0621, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 2.512e-06, |
|
"loss": 0.0603, |
|
"step": 2375 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 2.4120000000000004e-06, |
|
"loss": 0.0555, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.312e-06, |
|
"loss": 0.0498, |
|
"step": 2425 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 2.212e-06, |
|
"loss": 0.0311, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.1120000000000003e-06, |
|
"loss": 0.0341, |
|
"step": 2475 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 2.012e-06, |
|
"loss": 0.0343, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 1.912e-06, |
|
"loss": 0.0343, |
|
"step": 2525 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 1.8120000000000002e-06, |
|
"loss": 0.062, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 1.712e-06, |
|
"loss": 0.0566, |
|
"step": 2575 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 1.6120000000000002e-06, |
|
"loss": 0.0369, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 1.512e-06, |
|
"loss": 0.0261, |
|
"step": 2625 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 1.412e-06, |
|
"loss": 0.0382, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 1.3120000000000003e-06, |
|
"loss": 0.0359, |
|
"step": 2675 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 1.2120000000000002e-06, |
|
"loss": 0.0288, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 1.1120000000000001e-06, |
|
"loss": 0.0241, |
|
"step": 2725 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 1.012e-06, |
|
"loss": 0.0253, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 9.120000000000001e-07, |
|
"loss": 0.0272, |
|
"step": 2775 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 8.12e-07, |
|
"loss": 0.0288, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 7.12e-07, |
|
"loss": 0.0253, |
|
"step": 2825 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 6.12e-07, |
|
"loss": 0.0252, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 5.12e-07, |
|
"loss": 0.0304, |
|
"step": 2875 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 4.1200000000000004e-07, |
|
"loss": 0.0294, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 3.12e-07, |
|
"loss": 0.0349, |
|
"step": 2925 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 2.1200000000000002e-07, |
|
"loss": 0.0315, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 1.1200000000000001e-07, |
|
"loss": 0.0269, |
|
"step": 2975 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 1.2e-08, |
|
"loss": 0.0313, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"eval_loss": 0.18125878274440765, |
|
"eval_runtime": 5841.6004, |
|
"eval_samples_per_second": 1.736, |
|
"eval_steps_per_second": 0.109, |
|
"eval_wer": 9.977604008502885, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"step": 3000, |
|
"total_flos": 9.794132934524928e+19, |
|
"train_loss": 0.11344940463701884, |
|
"train_runtime": 35481.6673, |
|
"train_samples_per_second": 2.706, |
|
"train_steps_per_second": 0.085 |
|
} |
|
], |
|
"max_steps": 3000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 9.794132934524928e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|