| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.0198, | |
| "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": 5.000000000000001e-07, | |
| "loss": 3.076, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.7763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.7774, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.2284, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.0154, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-06, | |
| "loss": 0.3662, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.4258, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.5781, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.6681, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4686, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.5544, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6e-06, | |
| "loss": 0.5253, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.1806, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7e-06, | |
| "loss": 0.3124, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.4654, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.417, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.5e-06, | |
| "loss": 0.329, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9e-06, | |
| "loss": 0.4511, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.3265, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1291, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.295295774936676, | |
| "eval_runtime": 1223.0429, | |
| "eval_samples_per_second": 8.823, | |
| "eval_steps_per_second": 0.276, | |
| "eval_wer": 25.0681316779859, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.944444444444445e-06, | |
| "loss": 0.2684, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.88888888888889e-06, | |
| "loss": 0.3803, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.833333333333333e-06, | |
| "loss": 0.2907, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.2804, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.3529, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.666666666666667e-06, | |
| "loss": 0.1709, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.611111111111112e-06, | |
| "loss": 0.1081, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.2369, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.3028, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.2095, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.38888888888889e-06, | |
| "loss": 0.2095, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.2998, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.277777777777778e-06, | |
| "loss": 0.0884, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.222222222222224e-06, | |
| "loss": 0.1064, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 0.214, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.111111111111112e-06, | |
| "loss": 0.2348, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.055555555555556e-06, | |
| "loss": 0.1524, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9e-06, | |
| "loss": 0.1757, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 8.944444444444446e-06, | |
| "loss": 0.2374, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.0524, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 0.16263066232204437, | |
| "eval_runtime": 1237.1068, | |
| "eval_samples_per_second": 8.723, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 13.911839771596659, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.833333333333334e-06, | |
| "loss": 0.1126, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.777777777777778e-06, | |
| "loss": 0.1953, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.722222222222224e-06, | |
| "loss": 0.1616, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.1218, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 8.611111111111112e-06, | |
| "loss": 0.1598, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 8.555555555555556e-06, | |
| "loss": 0.1578, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 8.5e-06, | |
| "loss": 0.0386, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.1073, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 8.38888888888889e-06, | |
| "loss": 0.1719, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.1167, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 8.277777777777778e-06, | |
| "loss": 0.0989, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 8.222222222222222e-06, | |
| "loss": 0.1553, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 8.166666666666668e-06, | |
| "loss": 0.0849, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 8.111111111111112e-06, | |
| "loss": 0.0336, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.055555555555557e-06, | |
| "loss": 0.0949, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.142, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 7.944444444444445e-06, | |
| "loss": 0.0823, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 7.88888888888889e-06, | |
| "loss": 0.0739, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 7.833333333333333e-06, | |
| "loss": 0.135, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.0403, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "eval_loss": 0.08251597732305527, | |
| "eval_runtime": 1230.3126, | |
| "eval_samples_per_second": 8.771, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 6.544966907470692, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 7.722222222222223e-06, | |
| "loss": 0.033, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 7.666666666666667e-06, | |
| "loss": 0.0852, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 7.611111111111111e-06, | |
| "loss": 0.1076, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 0.053, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0596, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 7.444444444444445e-06, | |
| "loss": 0.1026, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 7.38888888888889e-06, | |
| "loss": 0.0194, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 0.0364, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 7.277777777777778e-06, | |
| "loss": 0.0809, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 7.222222222222223e-06, | |
| "loss": 0.0636, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 7.166666666666667e-06, | |
| "loss": 0.0366, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 0.0534, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 7.055555555555557e-06, | |
| "loss": 0.0643, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0124, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.03, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 6.88888888888889e-06, | |
| "loss": 0.0627, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 6.833333333333334e-06, | |
| "loss": 0.0392, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 6.777777777777779e-06, | |
| "loss": 0.0264, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 6.7222222222222235e-06, | |
| "loss": 0.0421, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0349, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 0.0408640094101429, | |
| "eval_runtime": 1201.4837, | |
| "eval_samples_per_second": 8.981, | |
| "eval_steps_per_second": 0.281, | |
| "eval_wer": 2.5652117489293595, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.6111111111111115e-06, | |
| "loss": 0.0101, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.555555555555556e-06, | |
| "loss": 0.0242, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.0492, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 6.444444444444445e-06, | |
| "loss": 0.0203, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 6.3888888888888885e-06, | |
| "loss": 0.0176, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 6.333333333333333e-06, | |
| "loss": 0.0355, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 6.277777777777778e-06, | |
| "loss": 0.0131, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.0093, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 6.166666666666667e-06, | |
| "loss": 0.0217, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 6.111111111111112e-06, | |
| "loss": 0.0276, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 6.055555555555555e-06, | |
| "loss": 0.0124, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 6e-06, | |
| "loss": 0.012, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.944444444444445e-06, | |
| "loss": 0.0238, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.88888888888889e-06, | |
| "loss": 0.0063, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 0.0085, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 0.0175, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 5.722222222222222e-06, | |
| "loss": 0.0158, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 5.666666666666667e-06, | |
| "loss": 0.0086, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 5.611111111111112e-06, | |
| "loss": 0.0102, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.0122, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "eval_loss": 0.017267020419239998, | |
| "eval_runtime": 1247.4451, | |
| "eval_samples_per_second": 8.65, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 0.6618505861487217, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.0042, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5.444444444444445e-06, | |
| "loss": 0.0068, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 5.388888888888889e-06, | |
| "loss": 0.014, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.0086, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 5.2777777777777785e-06, | |
| "loss": 0.0063, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 5.2222222222222226e-06, | |
| "loss": 0.0081, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 5.1666666666666675e-06, | |
| "loss": 0.0065, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 0.0039, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.0555555555555555e-06, | |
| "loss": 0.0063, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0096, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 4.944444444444445e-06, | |
| "loss": 0.0058, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 0.0051, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 4.833333333333333e-06, | |
| "loss": 0.0067, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 4.777777777777778e-06, | |
| "loss": 0.0045, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.722222222222222e-06, | |
| "loss": 0.0032, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.0051, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 4.611111111111112e-06, | |
| "loss": 0.0062, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 4.555555555555556e-06, | |
| "loss": 0.0041, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0042, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.0053, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "eval_loss": 0.006799217313528061, | |
| "eval_runtime": 1228.8049, | |
| "eval_samples_per_second": 8.782, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 0.08219059566552753, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 4.388888888888889e-06, | |
| "loss": 0.0023, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.333333333333334e-06, | |
| "loss": 0.0032, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 4.277777777777778e-06, | |
| "loss": 0.0044, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 0.0042, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0033, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 4.111111111111111e-06, | |
| "loss": 0.0039, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 4.055555555555556e-06, | |
| "loss": 0.0038, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0019, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.944444444444445e-06, | |
| "loss": 0.0029, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.88888888888889e-06, | |
| "loss": 0.0038, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.833333333333334e-06, | |
| "loss": 0.0035, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.777777777777778e-06, | |
| "loss": 0.0028, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.7222222222222225e-06, | |
| "loss": 0.0035, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 3.6666666666666666e-06, | |
| "loss": 0.0028, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 3.6111111111111115e-06, | |
| "loss": 0.0019, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 0.0026, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0033, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.444444444444445e-06, | |
| "loss": 0.003, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.3888888888888893e-06, | |
| "loss": 0.0025, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0032, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_loss": 0.0037031862884759903, | |
| "eval_runtime": 1247.7071, | |
| "eval_samples_per_second": 8.649, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 0.017303283298005796, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 20.03, | |
| "learning_rate": 3.277777777777778e-06, | |
| "loss": 0.0019, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.2222222222222227e-06, | |
| "loss": 0.0017, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.1666666666666667e-06, | |
| "loss": 0.0025, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.0029, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.055555555555556e-06, | |
| "loss": 0.0024, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0024, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 21.03, | |
| "learning_rate": 2.944444444444445e-06, | |
| "loss": 0.0028, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 21.03, | |
| "learning_rate": 2.888888888888889e-06, | |
| "loss": 0.0015, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 2.8333333333333335e-06, | |
| "loss": 0.0018, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 0.0024, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 2.7222222222222224e-06, | |
| "loss": 0.0026, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.0021, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 2.6111111111111113e-06, | |
| "loss": 0.0023, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 2.5555555555555557e-06, | |
| "loss": 0.0024, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0013, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.4444444444444447e-06, | |
| "loss": 0.0018, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.388888888888889e-06, | |
| "loss": 0.0023, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.3333333333333336e-06, | |
| "loss": 0.0023, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.277777777777778e-06, | |
| "loss": 0.0019, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.0022, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_loss": 0.0023553792852908373, | |
| "eval_runtime": 1205.8288, | |
| "eval_samples_per_second": 8.949, | |
| "eval_steps_per_second": 0.28, | |
| "eval_wer": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 23.03, | |
| "learning_rate": 2.166666666666667e-06, | |
| "loss": 0.0019, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 23.03, | |
| "learning_rate": 2.1111111111111114e-06, | |
| "loss": 0.0012, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.0555555555555555e-06, | |
| "loss": 0.0018, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0022, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 1.944444444444445e-06, | |
| "loss": 0.0021, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 1.888888888888889e-06, | |
| "loss": 0.0019, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 1.8333333333333333e-06, | |
| "loss": 0.0021, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.0014, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 1.7222222222222224e-06, | |
| "loss": 0.0013, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0018, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 1.6111111111111113e-06, | |
| "loss": 0.0021, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 1.5555555555555558e-06, | |
| "loss": 0.0018, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0018, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 1.4444444444444445e-06, | |
| "loss": 0.002, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 25.03, | |
| "learning_rate": 1.3888888888888892e-06, | |
| "loss": 0.0012, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.0014, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 1.2777777777777779e-06, | |
| "loss": 0.0018, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 1.2222222222222223e-06, | |
| "loss": 0.002, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 1.1666666666666668e-06, | |
| "loss": 0.0016, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.0018, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "eval_loss": 0.0017579125706106424, | |
| "eval_runtime": 1231.6359, | |
| "eval_samples_per_second": 8.762, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 26.03, | |
| "learning_rate": 1.0555555555555557e-06, | |
| "loss": 0.0019, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 26.03, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0011, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 9.444444444444445e-07, | |
| "loss": 0.0014, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.0018, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.0018, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 7.777777777777779e-07, | |
| "loss": 0.0016, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 7.222222222222222e-07, | |
| "loss": 0.0018, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.0016, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 6.111111111111112e-07, | |
| "loss": 0.001, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 5.555555555555555e-07, | |
| "loss": 0.0015, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0019, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.0017, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 3.8888888888888895e-07, | |
| "loss": 0.0015, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 3.3333333333333335e-07, | |
| "loss": 0.0018, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 2.7777777777777776e-07, | |
| "loss": 0.0014, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 2.2222222222222224e-07, | |
| "loss": 0.0011, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 1.6666666666666668e-07, | |
| "loss": 0.0015, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 1.1111111111111112e-07, | |
| "loss": 0.0018, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 5.555555555555556e-08, | |
| "loss": 0.0016, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.0016, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_loss": 0.001516498625278473, | |
| "eval_runtime": 1243.7778, | |
| "eval_samples_per_second": 8.676, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 0.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "step": 5000, | |
| "total_flos": 9.2138103687168e+19, | |
| "train_loss": 0.12212072040811181, | |
| "train_runtime": 32355.637, | |
| "train_samples_per_second": 9.89, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.2138103687168e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |