| { | |
| "best_metric": 34.623217922606926, | |
| "best_model_checkpoint": "./checkpoint-5000", | |
| "epoch": 92.0064, | |
| "eval_steps": 500, | |
| "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": 4.0000000000000003e-07, | |
| "loss": 1.7607, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 1.3297, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 0.8829, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.9000000000000002e-06, | |
| "loss": 0.7389, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.5364, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.88e-06, | |
| "loss": 0.4617, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.3800000000000007e-06, | |
| "loss": 0.3465, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.86e-06, | |
| "loss": 0.2559, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.360000000000001e-06, | |
| "loss": 0.2157, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.86e-06, | |
| "loss": 0.1294, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.36e-06, | |
| "loss": 0.1439, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 5.86e-06, | |
| "loss": 0.0834, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 6.360000000000001e-06, | |
| "loss": 0.0977, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 6.860000000000001e-06, | |
| "loss": 0.0593, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 7.360000000000001e-06, | |
| "loss": 0.0798, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.860000000000001e-06, | |
| "loss": 0.0495, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 8.36e-06, | |
| "loss": 0.0618, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.860000000000002e-06, | |
| "loss": 0.0597, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.360000000000002e-06, | |
| "loss": 0.0561, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.86e-06, | |
| "loss": 0.0515, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.6733026504516602, | |
| "eval_runtime": 110.5203, | |
| "eval_samples_per_second": 3.474, | |
| "eval_steps_per_second": 0.217, | |
| "eval_wer": 42.484725050916495, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 9.960000000000001e-06, | |
| "loss": 0.0518, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.904444444444445e-06, | |
| "loss": 0.0528, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 9.84888888888889e-06, | |
| "loss": 0.0451, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.793333333333333e-06, | |
| "loss": 0.0403, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 9.737777777777779e-06, | |
| "loss": 0.0382, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 9.682222222222223e-06, | |
| "loss": 0.0432, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 9.626666666666667e-06, | |
| "loss": 0.0251, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 9.571111111111113e-06, | |
| "loss": 0.0238, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 9.515555555555557e-06, | |
| "loss": 0.0256, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 9.460000000000001e-06, | |
| "loss": 0.0285, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 9.404444444444445e-06, | |
| "loss": 0.0224, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 9.348888888888889e-06, | |
| "loss": 0.0171, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 9.293333333333335e-06, | |
| "loss": 0.0144, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 9.237777777777779e-06, | |
| "loss": 0.0224, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 9.182222222222223e-06, | |
| "loss": 0.0189, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 9.126666666666667e-06, | |
| "loss": 0.0128, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 9.07111111111111e-06, | |
| "loss": 0.0114, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 9.015555555555557e-06, | |
| "loss": 0.012, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 8.96e-06, | |
| "loss": 0.0137, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 8.904444444444446e-06, | |
| "loss": 0.0101, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "eval_loss": 0.680969774723053, | |
| "eval_runtime": 105.2408, | |
| "eval_samples_per_second": 3.649, | |
| "eval_steps_per_second": 0.228, | |
| "eval_wer": 37.596741344195515, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 8.848888888888889e-06, | |
| "loss": 0.0115, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 8.793333333333334e-06, | |
| "loss": 0.0065, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 8.737777777777778e-06, | |
| "loss": 0.012, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 8.682222222222222e-06, | |
| "loss": 0.008, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 8.626666666666668e-06, | |
| "loss": 0.0106, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 8.571111111111112e-06, | |
| "loss": 0.0084, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 8.515555555555556e-06, | |
| "loss": 0.0065, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 8.46e-06, | |
| "loss": 0.0066, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 8.404444444444444e-06, | |
| "loss": 0.0118, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.34888888888889e-06, | |
| "loss": 0.0077, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 8.293333333333334e-06, | |
| "loss": 0.0083, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 8.237777777777778e-06, | |
| "loss": 0.0111, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 8.182222222222222e-06, | |
| "loss": 0.0075, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 8.126666666666668e-06, | |
| "loss": 0.0083, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 8.071111111111112e-06, | |
| "loss": 0.0043, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 8.015555555555556e-06, | |
| "loss": 0.0074, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 7.960000000000002e-06, | |
| "loss": 0.0047, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 7.904444444444444e-06, | |
| "loss": 0.0057, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 7.84888888888889e-06, | |
| "loss": 0.0077, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 7.793333333333334e-06, | |
| "loss": 0.0074, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "eval_loss": 0.7185311317443848, | |
| "eval_runtime": 104.8405, | |
| "eval_samples_per_second": 3.663, | |
| "eval_steps_per_second": 0.229, | |
| "eval_wer": 38.085539714867615, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 7.737777777777778e-06, | |
| "loss": 0.0059, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 7.682222222222224e-06, | |
| "loss": 0.0085, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 7.626666666666668e-06, | |
| "loss": 0.0076, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 7.571111111111112e-06, | |
| "loss": 0.0019, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 7.515555555555556e-06, | |
| "loss": 0.0078, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 7.4600000000000006e-06, | |
| "loss": 0.0032, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 7.4044444444444455e-06, | |
| "loss": 0.0027, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 7.3488888888888895e-06, | |
| "loss": 0.0034, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 7.2933333333333335e-06, | |
| "loss": 0.0036, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 7.237777777777778e-06, | |
| "loss": 0.0024, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 7.1822222222222224e-06, | |
| "loss": 0.001, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 7.126666666666667e-06, | |
| "loss": 0.0007, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 7.071111111111112e-06, | |
| "loss": 0.0057, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 7.015555555555556e-06, | |
| "loss": 0.0052, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 6.96e-06, | |
| "loss": 0.0043, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6.904444444444444e-06, | |
| "loss": 0.0021, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 6.848888888888889e-06, | |
| "loss": 0.0021, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 6.793333333333334e-06, | |
| "loss": 0.004, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 6.737777777777779e-06, | |
| "loss": 0.0016, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 6.682222222222223e-06, | |
| "loss": 0.0009, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.6986598372459412, | |
| "eval_runtime": 104.187, | |
| "eval_samples_per_second": 3.686, | |
| "eval_steps_per_second": 0.23, | |
| "eval_wer": 35.5193482688391, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 6.626666666666667e-06, | |
| "loss": 0.0014, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 6.571111111111111e-06, | |
| "loss": 0.0008, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 6.515555555555556e-06, | |
| "loss": 0.0012, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 6.460000000000001e-06, | |
| "loss": 0.0007, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 6.404444444444446e-06, | |
| "loss": 0.0005, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 6.348888888888889e-06, | |
| "loss": 0.0025, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 6.293333333333334e-06, | |
| "loss": 0.0003, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 6.237777777777778e-06, | |
| "loss": 0.0004, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 6.182222222222223e-06, | |
| "loss": 0.0003, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 6.126666666666668e-06, | |
| "loss": 0.0002, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 6.0711111111111125e-06, | |
| "loss": 0.0002, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 6.015555555555556e-06, | |
| "loss": 0.0002, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 5.9600000000000005e-06, | |
| "loss": 0.0002, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 5.9044444444444446e-06, | |
| "loss": 0.0002, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 5.8488888888888895e-06, | |
| "loss": 0.0002, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 5.793333333333334e-06, | |
| "loss": 0.0002, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.737777777777778e-06, | |
| "loss": 0.0002, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 5.682222222222222e-06, | |
| "loss": 0.0002, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 5.626666666666667e-06, | |
| "loss": 0.0002, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 5.571111111111111e-06, | |
| "loss": 0.0002, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.7392615675926208, | |
| "eval_runtime": 104.4509, | |
| "eval_samples_per_second": 3.676, | |
| "eval_steps_per_second": 0.23, | |
| "eval_wer": 35.03054989816701, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 5.515555555555556e-06, | |
| "loss": 0.0002, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 5.460000000000001e-06, | |
| "loss": 0.0002, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 5.404444444444444e-06, | |
| "loss": 0.0001, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 5.348888888888889e-06, | |
| "loss": 0.0001, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 5.293333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 5.237777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 5.182222222222223e-06, | |
| "loss": 0.0001, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 5.126666666666668e-06, | |
| "loss": 0.0001, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 50.01, | |
| "learning_rate": 5.071111111111111e-06, | |
| "loss": 0.0001, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 50.01, | |
| "learning_rate": 5.015555555555556e-06, | |
| "loss": 0.0001, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 4.960000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 51.01, | |
| "learning_rate": 4.904444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 4.848888888888889e-06, | |
| "loss": 0.0001, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 52.01, | |
| "learning_rate": 4.793333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 4.737777777777779e-06, | |
| "loss": 0.0001, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 53.01, | |
| "learning_rate": 4.682222222222223e-06, | |
| "loss": 0.0001, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 4.626666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 54.01, | |
| "learning_rate": 4.571111111111112e-06, | |
| "loss": 0.0001, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 4.515555555555556e-06, | |
| "loss": 0.0001, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 55.01, | |
| "learning_rate": 4.4600000000000005e-06, | |
| "loss": 0.0001, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 55.01, | |
| "eval_loss": 0.7602861523628235, | |
| "eval_runtime": 104.4035, | |
| "eval_samples_per_second": 3.678, | |
| "eval_steps_per_second": 0.23, | |
| "eval_wer": 35.03054989816701, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 4.404444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 56.01, | |
| "learning_rate": 4.348888888888889e-06, | |
| "loss": 0.0001, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 56.01, | |
| "learning_rate": 4.2933333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 4.2377777777777775e-06, | |
| "loss": 0.0001, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 57.01, | |
| "learning_rate": 4.182222222222222e-06, | |
| "loss": 0.0001, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 4.126666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 58.01, | |
| "learning_rate": 4.071111111111111e-06, | |
| "loss": 0.0001, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 4.015555555555556e-06, | |
| "loss": 0.0001, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 59.01, | |
| "learning_rate": 3.96e-06, | |
| "loss": 0.0001, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 3.904444444444444e-06, | |
| "loss": 0.0001, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 60.01, | |
| "learning_rate": 3.848888888888889e-06, | |
| "loss": 0.0001, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 3.793333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 61.01, | |
| "learning_rate": 3.737777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 3.6822222222222225e-06, | |
| "loss": 0.0001, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 62.01, | |
| "learning_rate": 3.6266666666666674e-06, | |
| "loss": 0.0001, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 62.01, | |
| "learning_rate": 3.5711111111111114e-06, | |
| "loss": 0.0001, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 3.515555555555556e-06, | |
| "loss": 0.0001, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 63.01, | |
| "learning_rate": 3.46e-06, | |
| "loss": 0.0001, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.404444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 64.01, | |
| "learning_rate": 3.3488888888888892e-06, | |
| "loss": 0.0001, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 64.01, | |
| "eval_loss": 0.7738750576972961, | |
| "eval_runtime": 104.8601, | |
| "eval_samples_per_second": 3.662, | |
| "eval_steps_per_second": 0.229, | |
| "eval_wer": 34.86761710794297, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 3.2933333333333333e-06, | |
| "loss": 0.0001, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 65.01, | |
| "learning_rate": 3.237777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 3.1822222222222226e-06, | |
| "loss": 0.0001, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 66.01, | |
| "learning_rate": 3.1266666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 3.0711111111111115e-06, | |
| "loss": 0.0001, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 67.01, | |
| "learning_rate": 3.015555555555556e-06, | |
| "loss": 0.0001, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 2.96e-06, | |
| "loss": 0.0001, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 68.01, | |
| "learning_rate": 2.904444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 68.01, | |
| "learning_rate": 2.8488888888888894e-06, | |
| "loss": 0.0001, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 2.7933333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 69.01, | |
| "learning_rate": 2.7377777777777783e-06, | |
| "loss": 0.0001, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 2.6822222222222223e-06, | |
| "loss": 0.0001, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 70.01, | |
| "learning_rate": 2.6266666666666668e-06, | |
| "loss": 0.0001, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 2.5711111111111112e-06, | |
| "loss": 0.0001, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 71.01, | |
| "learning_rate": 2.5155555555555557e-06, | |
| "loss": 0.0001, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 2.46e-06, | |
| "loss": 0.0001, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 72.01, | |
| "learning_rate": 2.4044444444444446e-06, | |
| "loss": 0.0001, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 2.348888888888889e-06, | |
| "loss": 0.0001, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 73.01, | |
| "learning_rate": 2.2933333333333335e-06, | |
| "loss": 0.0001, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 2.237777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.7832472920417786, | |
| "eval_runtime": 104.6874, | |
| "eval_samples_per_second": 3.668, | |
| "eval_steps_per_second": 0.229, | |
| "eval_wer": 34.82688391038696, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 74.01, | |
| "learning_rate": 2.1822222222222225e-06, | |
| "loss": 0.0001, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 74.01, | |
| "learning_rate": 2.126666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 2.0711111111111114e-06, | |
| "loss": 0.0001, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 75.01, | |
| "learning_rate": 2.0155555555555554e-06, | |
| "loss": 0.0001, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 1.9600000000000003e-06, | |
| "loss": 0.0001, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 76.01, | |
| "learning_rate": 1.9044444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 1.848888888888889e-06, | |
| "loss": 0.0001, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 77.01, | |
| "learning_rate": 1.7933333333333337e-06, | |
| "loss": 0.0001, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 1.737777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 78.01, | |
| "learning_rate": 1.6822222222222224e-06, | |
| "loss": 0.0001, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 1.6266666666666666e-06, | |
| "loss": 0.0001, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 79.01, | |
| "learning_rate": 1.5711111111111113e-06, | |
| "loss": 0.0001, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.5155555555555558e-06, | |
| "loss": 0.0001, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 80.01, | |
| "learning_rate": 1.46e-06, | |
| "loss": 0.0001, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "learning_rate": 1.4044444444444447e-06, | |
| "loss": 0.0001, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 81.01, | |
| "learning_rate": 1.3488888888888891e-06, | |
| "loss": 0.0001, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 81.01, | |
| "learning_rate": 1.2933333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 1.2377777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 82.01, | |
| "learning_rate": 1.1822222222222223e-06, | |
| "loss": 0.0001, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "learning_rate": 1.1266666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 0.7895247936248779, | |
| "eval_runtime": 104.5178, | |
| "eval_samples_per_second": 3.674, | |
| "eval_steps_per_second": 0.23, | |
| "eval_wer": 34.90835030549898, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 83.01, | |
| "learning_rate": 1.0711111111111112e-06, | |
| "loss": 0.0001, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 1.0155555555555557e-06, | |
| "loss": 0.0001, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 84.01, | |
| "learning_rate": 9.600000000000001e-07, | |
| "loss": 0.0001, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 9.044444444444445e-07, | |
| "loss": 0.0001, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 85.01, | |
| "learning_rate": 8.488888888888889e-07, | |
| "loss": 0.0001, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "learning_rate": 7.933333333333335e-07, | |
| "loss": 0.0001, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 86.01, | |
| "learning_rate": 7.377777777777779e-07, | |
| "loss": 0.0001, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "learning_rate": 6.822222222222223e-07, | |
| "loss": 0.0001, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 87.01, | |
| "learning_rate": 6.266666666666667e-07, | |
| "loss": 0.0001, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 87.01, | |
| "learning_rate": 5.711111111111111e-07, | |
| "loss": 0.0001, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 5.155555555555556e-07, | |
| "loss": 0.0001, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 88.01, | |
| "learning_rate": 4.6000000000000004e-07, | |
| "loss": 0.0001, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "learning_rate": 4.0444444444444445e-07, | |
| "loss": 0.0001, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 89.01, | |
| "learning_rate": 3.488888888888889e-07, | |
| "loss": 0.0001, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 2.9333333333333337e-07, | |
| "loss": 0.0001, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 90.01, | |
| "learning_rate": 2.3777777777777777e-07, | |
| "loss": 0.0001, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "learning_rate": 1.8222222222222226e-07, | |
| "loss": 0.0001, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 91.01, | |
| "learning_rate": 1.2666666666666666e-07, | |
| "loss": 0.0001, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "learning_rate": 7.111111111111112e-08, | |
| "loss": 0.0001, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 92.01, | |
| "learning_rate": 1.5555555555555557e-08, | |
| "loss": 0.0001, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 92.01, | |
| "eval_loss": 0.7918470501899719, | |
| "eval_runtime": 104.4946, | |
| "eval_samples_per_second": 3.675, | |
| "eval_steps_per_second": 0.23, | |
| "eval_wer": 34.623217922606926, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 92.01, | |
| "step": 5000, | |
| "total_flos": 1.69853681664e+20, | |
| "train_loss": 0.04092751889359206, | |
| "train_runtime": 27870.4476, | |
| "train_samples_per_second": 2.87, | |
| "train_steps_per_second": 0.179 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 1000, | |
| "total_flos": 1.69853681664e+20, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |