| { | |
| "best_metric": 50.49849292835613, | |
| "best_model_checkpoint": "Whisper-Small-Common-Voice/checkpoint-500", | |
| "epoch": 15.582391897156214, | |
| "eval_steps": 100, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-09, | |
| "loss": 0.0025, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-08, | |
| "loss": 0.0013, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.5e-08, | |
| "loss": 0.0043, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2e-08, | |
| "loss": 0.0022, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.8829813003540039, | |
| "eval_runtime": 1221.2319, | |
| "eval_samples_per_second": 5.03, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 51.01553443079063, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.5e-08, | |
| "loss": 0.0003, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3e-08, | |
| "loss": 0.0025, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.4999999999999996e-08, | |
| "loss": 0.0013, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4e-08, | |
| "loss": 0.0033, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.8824975490570068, | |
| "eval_runtime": 1222.9845, | |
| "eval_samples_per_second": 5.023, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 51.020171574310226, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.5e-08, | |
| "loss": 0.0007, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5e-08, | |
| "loss": 0.0025, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.5e-08, | |
| "loss": 0.0021, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6e-08, | |
| "loss": 0.0045, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.8818580508232117, | |
| "eval_runtime": 1225.0712, | |
| "eval_samples_per_second": 5.014, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 51.00162300023185, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.5e-08, | |
| "loss": 0.0018, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 6.999999999999999e-08, | |
| "loss": 0.004, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.5e-08, | |
| "loss": 0.0013, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8e-08, | |
| "loss": 0.0019, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.8799974322319031, | |
| "eval_runtime": 1228.4754, | |
| "eval_samples_per_second": 5.001, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 51.2033387433341, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.5e-08, | |
| "loss": 0.0467, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9e-08, | |
| "loss": 0.0027, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.499999999999999e-08, | |
| "loss": 0.0026, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-07, | |
| "loss": 0.0048, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.8783090114593506, | |
| "eval_runtime": 1252.7544, | |
| "eval_samples_per_second": 4.904, | |
| "eval_steps_per_second": 0.491, | |
| "eval_wer": 50.49849292835613, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.973684210526315e-08, | |
| "loss": 0.0018, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.94736842105263e-08, | |
| "loss": 0.0018, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.921052631578946e-08, | |
| "loss": 0.055, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.894736842105262e-08, | |
| "loss": 0.0042, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.8751734495162964, | |
| "eval_runtime": 1290.9321, | |
| "eval_samples_per_second": 4.759, | |
| "eval_steps_per_second": 0.476, | |
| "eval_wer": 51.09668444238349, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.868421052631579e-08, | |
| "loss": 0.0043, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.842105263157894e-08, | |
| "loss": 0.0021, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.815789473684211e-08, | |
| "loss": 0.0022, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.789473684210527e-08, | |
| "loss": 0.0024, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.874126136302948, | |
| "eval_runtime": 1224.1894, | |
| "eval_samples_per_second": 5.018, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.03802457686065, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.763157894736842e-08, | |
| "loss": 0.0039, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.736842105263158e-08, | |
| "loss": 0.0033, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.710526315789473e-08, | |
| "loss": 0.0002, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.684210526315789e-08, | |
| "loss": 0.0002, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.8719862103462219, | |
| "eval_runtime": 1217.5279, | |
| "eval_samples_per_second": 5.045, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 51.514027359146766, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 9.657894736842104e-08, | |
| "loss": 0.0006, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.63157894736842e-08, | |
| "loss": 0.0002, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.605263157894737e-08, | |
| "loss": 0.0025, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.578947368421052e-08, | |
| "loss": 0.0011, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.8716684579849243, | |
| "eval_runtime": 1209.9899, | |
| "eval_samples_per_second": 5.077, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 51.48156735450963, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.552631578947368e-08, | |
| "loss": 0.0004, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.526315789473683e-08, | |
| "loss": 0.0015, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.499999999999999e-08, | |
| "loss": 0.0023, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.473684210526315e-08, | |
| "loss": 0.0008, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.8708853125572205, | |
| "eval_runtime": 1209.0095, | |
| "eval_samples_per_second": 5.081, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 50.948295849756555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.447368421052631e-08, | |
| "loss": 0.0022, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.421052631578947e-08, | |
| "loss": 0.0021, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.394736842105263e-08, | |
| "loss": 0.0453, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.368421052631578e-08, | |
| "loss": 0.0035, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.8685131669044495, | |
| "eval_runtime": 1207.1634, | |
| "eval_samples_per_second": 5.089, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 51.36332019476003, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.342105263157895e-08, | |
| "loss": 0.0051, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 9.31578947368421e-08, | |
| "loss": 0.0037, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.289473684210526e-08, | |
| "loss": 0.0486, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.263157894736842e-08, | |
| "loss": 0.002, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.8655429482460022, | |
| "eval_runtime": 1212.5684, | |
| "eval_samples_per_second": 5.066, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 52.02643171806167, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 9.236842105263157e-08, | |
| "loss": 0.0002, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.210526315789473e-08, | |
| "loss": 0.0014, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 9.184210526315788e-08, | |
| "loss": 0.0019, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.157894736842104e-08, | |
| "loss": 0.0024, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.864643394947052, | |
| "eval_runtime": 1219.1646, | |
| "eval_samples_per_second": 5.039, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.6431718061674, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.131578947368421e-08, | |
| "loss": 0.0014, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.105263157894736e-08, | |
| "loss": 0.0012, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.078947368421053e-08, | |
| "loss": 0.0006, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.052631578947369e-08, | |
| "loss": 0.0013, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.8650274872779846, | |
| "eval_runtime": 1222.8432, | |
| "eval_samples_per_second": 5.024, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 52.04729886389984, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 9.026315789473684e-08, | |
| "loss": 0.0046, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 9e-08, | |
| "loss": 0.0035, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.973684210526315e-08, | |
| "loss": 0.0012, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.947368421052631e-08, | |
| "loss": 0.0006, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.8591874241828918, | |
| "eval_runtime": 1225.6385, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 51.81312311616044, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.921052631578947e-08, | |
| "loss": 0.0008, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.894736842105262e-08, | |
| "loss": 0.0002, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.868421052631579e-08, | |
| "loss": 0.0005, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.842105263157895e-08, | |
| "loss": 0.0002, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.8596690893173218, | |
| "eval_runtime": 1221.8742, | |
| "eval_samples_per_second": 5.028, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 51.71110595872942, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.81578947368421e-08, | |
| "loss": 0.0006, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.789473684210526e-08, | |
| "loss": 0.0016, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.763157894736841e-08, | |
| "loss": 0.0024, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 8.736842105263158e-08, | |
| "loss": 0.0468, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.8583779335021973, | |
| "eval_runtime": 1213.501, | |
| "eval_samples_per_second": 5.062, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 51.660097380013916, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 8.710526315789474e-08, | |
| "loss": 0.049, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 8.684210526315789e-08, | |
| "loss": 0.0011, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 8.657894736842105e-08, | |
| "loss": 0.0015, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 8.63157894736842e-08, | |
| "loss": 0.0034, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.8571881055831909, | |
| "eval_runtime": 1219.6854, | |
| "eval_samples_per_second": 5.037, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 51.660097380013916, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 8.605263157894737e-08, | |
| "loss": 0.0013, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.578947368421053e-08, | |
| "loss": 0.0013, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.552631578947368e-08, | |
| "loss": 0.0008, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 8.526315789473684e-08, | |
| "loss": 0.0009, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.857424259185791, | |
| "eval_runtime": 1218.2619, | |
| "eval_samples_per_second": 5.042, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 51.38882448411778, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.5e-08, | |
| "loss": 0.002, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 8.473684210526315e-08, | |
| "loss": 0.0007, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.44736842105263e-08, | |
| "loss": 0.0008, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 8.421052631578946e-08, | |
| "loss": 0.0002, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.8559578061103821, | |
| "eval_runtime": 1215.067, | |
| "eval_samples_per_second": 5.056, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 51.483885926269416, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.394736842105263e-08, | |
| "loss": 0.0014, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 8.368421052631578e-08, | |
| "loss": 0.0028, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 8.342105263157895e-08, | |
| "loss": 0.0006, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 8.315789473684211e-08, | |
| "loss": 0.0003, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 0.8543346524238586, | |
| "eval_runtime": 1227.9498, | |
| "eval_samples_per_second": 5.003, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.37189891027128, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 8.289473684210526e-08, | |
| "loss": 0.0002, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 8.263157894736842e-08, | |
| "loss": 0.0005, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 8.236842105263158e-08, | |
| "loss": 0.0002, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 8.210526315789473e-08, | |
| "loss": 0.0019, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "eval_loss": 0.8546163439750671, | |
| "eval_runtime": 1228.9996, | |
| "eval_samples_per_second": 4.998, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.33480176211454, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 8.184210526315789e-08, | |
| "loss": 0.0012, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 8.157894736842104e-08, | |
| "loss": 0.0009, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 8.131578947368421e-08, | |
| "loss": 0.0026, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 8.105263157894737e-08, | |
| "loss": 0.0003, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_loss": 0.8546996712684631, | |
| "eval_runtime": 1227.525, | |
| "eval_samples_per_second": 5.004, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.67795038256434, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 8.078947368421052e-08, | |
| "loss": 0.0002, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 8.052631578947368e-08, | |
| "loss": 0.0006, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 8.026315789473685e-08, | |
| "loss": 0.0009, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 8e-08, | |
| "loss": 0.0015, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_loss": 0.855933427810669, | |
| "eval_runtime": 1221.4085, | |
| "eval_samples_per_second": 5.029, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.43913749130535, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 7.973684210526316e-08, | |
| "loss": 0.0035, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 7.947368421052631e-08, | |
| "loss": 0.0459, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 7.921052631578947e-08, | |
| "loss": 0.0036, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 7.894736842105262e-08, | |
| "loss": 0.0013, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_loss": 0.8527611494064331, | |
| "eval_runtime": 1231.6304, | |
| "eval_samples_per_second": 4.988, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 52.61071180153025, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 7.868421052631579e-08, | |
| "loss": 0.0002, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 7.842105263157895e-08, | |
| "loss": 0.0007, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.81578947368421e-08, | |
| "loss": 0.0369, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.789473684210526e-08, | |
| "loss": 0.0008, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.8517388105392456, | |
| "eval_runtime": 1229.8207, | |
| "eval_samples_per_second": 4.995, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.24437746348249, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 7.763157894736841e-08, | |
| "loss": 0.0016, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 7.736842105263157e-08, | |
| "loss": 0.0008, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 7.710526315789473e-08, | |
| "loss": 0.0002, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 7.684210526315788e-08, | |
| "loss": 0.0432, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_loss": 0.8489501476287842, | |
| "eval_runtime": 1218.7862, | |
| "eval_samples_per_second": 5.04, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 51.22420588917227, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 7.657894736842105e-08, | |
| "loss": 0.0014, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 7.63157894736842e-08, | |
| "loss": 0.0002, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.605263157894737e-08, | |
| "loss": 0.0003, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 7.578947368421053e-08, | |
| "loss": 0.0002, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "eval_loss": 0.8481741547584534, | |
| "eval_runtime": 1224.6985, | |
| "eval_samples_per_second": 5.016, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 51.347090192441456, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 7.552631578947369e-08, | |
| "loss": 0.0341, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 7.526315789473684e-08, | |
| "loss": 0.0008, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 7.5e-08, | |
| "loss": 0.0005, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 7.473684210526315e-08, | |
| "loss": 0.0014, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_loss": 0.8483814597129822, | |
| "eval_runtime": 1220.0018, | |
| "eval_samples_per_second": 5.035, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 51.28217018316717, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 7.447368421052631e-08, | |
| "loss": 0.0016, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 7.421052631578946e-08, | |
| "loss": 0.0003, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 7.394736842105262e-08, | |
| "loss": 0.0003, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 7.368421052631579e-08, | |
| "loss": 0.0018, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_loss": 0.8505555987358093, | |
| "eval_runtime": 1221.205, | |
| "eval_samples_per_second": 5.03, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.086714583816374, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 7.342105263157894e-08, | |
| "loss": 0.0005, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 7.315789473684211e-08, | |
| "loss": 0.0006, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 7.289473684210527e-08, | |
| "loss": 0.0002, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 7.263157894736842e-08, | |
| "loss": 0.0007, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.8507622480392456, | |
| "eval_runtime": 1227.2719, | |
| "eval_samples_per_second": 5.005, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.6408532344076, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 7.236842105263158e-08, | |
| "loss": 0.004, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 7.210526315789473e-08, | |
| "loss": 0.0019, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 7.184210526315789e-08, | |
| "loss": 0.0007, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 7.157894736842105e-08, | |
| "loss": 0.001, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.8503895998001099, | |
| "eval_runtime": 1226.724, | |
| "eval_samples_per_second": 5.008, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.50405750057965, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.13157894736842e-08, | |
| "loss": 0.0003, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 7.105263157894737e-08, | |
| "loss": 0.0002, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 7.078947368421052e-08, | |
| "loss": 0.0002, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 7.052631578947368e-08, | |
| "loss": 0.0009, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_loss": 0.8513568043708801, | |
| "eval_runtime": 1232.2177, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 52.53883607697658, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 7.026315789473684e-08, | |
| "loss": 0.0409, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 6.999999999999999e-08, | |
| "loss": 0.0014, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 6.973684210526315e-08, | |
| "loss": 0.0008, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 6.947368421052632e-08, | |
| "loss": 0.0359, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "eval_loss": 0.8513284921646118, | |
| "eval_runtime": 1228.2976, | |
| "eval_samples_per_second": 5.001, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.65012752144679, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 6.921052631578947e-08, | |
| "loss": 0.0005, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 6.894736842105263e-08, | |
| "loss": 0.0007, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 6.868421052631578e-08, | |
| "loss": 0.0005, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 6.842105263157895e-08, | |
| "loss": 0.0008, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 0.8511779308319092, | |
| "eval_runtime": 1229.3458, | |
| "eval_samples_per_second": 4.997, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.91444470206352, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 6.815789473684211e-08, | |
| "loss": 0.0016, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 6.789473684210526e-08, | |
| "loss": 0.0025, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 6.763157894736842e-08, | |
| "loss": 0.0004, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 6.736842105263157e-08, | |
| "loss": 0.0006, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_loss": 0.8511531352996826, | |
| "eval_runtime": 1231.5789, | |
| "eval_samples_per_second": 4.988, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 53.065151866450265, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 6.710526315789473e-08, | |
| "loss": 0.0009, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 6.684210526315788e-08, | |
| "loss": 0.0003, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 6.657894736842104e-08, | |
| "loss": 0.0005, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 6.631578947368421e-08, | |
| "loss": 0.0003, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 0.8500731587409973, | |
| "eval_runtime": 1231.5834, | |
| "eval_samples_per_second": 4.988, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 52.884303269186184, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 6.605263157894736e-08, | |
| "loss": 0.0003, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 6.578947368421053e-08, | |
| "loss": 0.001, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 6.552631578947369e-08, | |
| "loss": 0.0002, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 6.526315789473684e-08, | |
| "loss": 0.0017, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "eval_loss": 0.8508526086807251, | |
| "eval_runtime": 1221.0869, | |
| "eval_samples_per_second": 5.031, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.97009042429863, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 6.5e-08, | |
| "loss": 0.0002, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 6.473684210526316e-08, | |
| "loss": 0.0002, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 6.447368421052631e-08, | |
| "loss": 0.0002, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 6.421052631578947e-08, | |
| "loss": 0.0014, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "eval_loss": 0.8512513637542725, | |
| "eval_runtime": 1229.7364, | |
| "eval_samples_per_second": 4.995, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 53.2738233248319, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 6.394736842105262e-08, | |
| "loss": 0.0002, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 6.368421052631579e-08, | |
| "loss": 0.0004, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 6.342105263157895e-08, | |
| "loss": 0.0004, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 6.31578947368421e-08, | |
| "loss": 0.0008, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "eval_loss": 0.8512950539588928, | |
| "eval_runtime": 1229.5214, | |
| "eval_samples_per_second": 4.996, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 53.57060051008579, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 6.289473684210526e-08, | |
| "loss": 0.0009, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 6.263157894736841e-08, | |
| "loss": 0.0004, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 6.236842105263158e-08, | |
| "loss": 0.0022, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 6.210526315789474e-08, | |
| "loss": 0.0361, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 0.8503543138504028, | |
| "eval_runtime": 1231.2351, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 53.99721771388825, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 6.184210526315789e-08, | |
| "loss": 0.0002, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 6.157894736842105e-08, | |
| "loss": 0.0008, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 6.13157894736842e-08, | |
| "loss": 0.0003, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 6.105263157894737e-08, | |
| "loss": 0.0006, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_loss": 0.8513213396072388, | |
| "eval_runtime": 1223.0874, | |
| "eval_samples_per_second": 5.023, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 53.58219336888477, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 6.078947368421053e-08, | |
| "loss": 0.0002, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 6.052631578947368e-08, | |
| "loss": 0.0013, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 6.026315789473684e-08, | |
| "loss": 0.0003, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 6e-08, | |
| "loss": 0.0002, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_loss": 0.852211594581604, | |
| "eval_runtime": 1232.4793, | |
| "eval_samples_per_second": 4.984, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 53.674936239276605, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 5.973684210526315e-08, | |
| "loss": 0.0008, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 5.947368421052631e-08, | |
| "loss": 0.0002, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 5.921052631578947e-08, | |
| "loss": 0.0002, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 5.8947368421052623e-08, | |
| "loss": 0.0009, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_loss": 0.852275013923645, | |
| "eval_runtime": 1230.9929, | |
| "eval_samples_per_second": 4.99, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 53.52191050313008, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 5.868421052631579e-08, | |
| "loss": 0.0002, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 5.842105263157895e-08, | |
| "loss": 0.001, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 5.81578947368421e-08, | |
| "loss": 0.0411, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.7894736842105265e-08, | |
| "loss": 0.0009, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 0.8531178832054138, | |
| "eval_runtime": 1230.5087, | |
| "eval_samples_per_second": 4.992, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 53.28077904011129, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 5.763157894736842e-08, | |
| "loss": 0.0003, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 5.7368421052631576e-08, | |
| "loss": 0.0002, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 5.710526315789473e-08, | |
| "loss": 0.0365, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 5.6842105263157894e-08, | |
| "loss": 0.0006, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "eval_loss": 0.8536715507507324, | |
| "eval_runtime": 1227.1668, | |
| "eval_samples_per_second": 5.006, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.949223278460465, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 5.657894736842105e-08, | |
| "loss": 0.0002, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 5.6315789473684205e-08, | |
| "loss": 0.0004, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 5.605263157894736e-08, | |
| "loss": 0.0002, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 5.5789473684210516e-08, | |
| "loss": 0.0006, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "eval_loss": 0.8536776304244995, | |
| "eval_runtime": 1226.3591, | |
| "eval_samples_per_second": 5.009, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.9909575701368, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 5.552631578947368e-08, | |
| "loss": 0.0381, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 5.526315789473685e-08, | |
| "loss": 0.0005, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 5.5e-08, | |
| "loss": 0.0005, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 5.473684210526316e-08, | |
| "loss": 0.0002, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_loss": 0.8543317914009094, | |
| "eval_runtime": 1225.8673, | |
| "eval_samples_per_second": 5.011, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.603756086250876, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 5.4473684210526314e-08, | |
| "loss": 0.0005, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 5.4210526315789476e-08, | |
| "loss": 0.0008, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 5.394736842105263e-08, | |
| "loss": 0.0005, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 5.368421052631579e-08, | |
| "loss": 0.0006, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "eval_loss": 0.8541797995567322, | |
| "eval_runtime": 1233.7118, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 0.498, | |
| "eval_wer": 52.7567818223974, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 5.342105263157894e-08, | |
| "loss": 0.0005, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 5.3157894736842105e-08, | |
| "loss": 0.0003, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 5.289473684210526e-08, | |
| "loss": 0.0002, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 5.2631578947368416e-08, | |
| "loss": 0.0002, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "eval_loss": 0.854214608669281, | |
| "eval_runtime": 1225.6266, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.956178993739854, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 5.236842105263157e-08, | |
| "loss": 0.0002, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 5.210526315789473e-08, | |
| "loss": 0.0002, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 5.184210526315789e-08, | |
| "loss": 0.0009, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 5.157894736842106e-08, | |
| "loss": 0.0003, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_loss": 0.8550341129302979, | |
| "eval_runtime": 1229.6172, | |
| "eval_samples_per_second": 4.996, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 53.14862044980292, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 5.1315789473684213e-08, | |
| "loss": 0.0003, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 5.105263157894737e-08, | |
| "loss": 0.0045, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 5.0789473684210525e-08, | |
| "loss": 0.0002, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 5.0526315789473687e-08, | |
| "loss": 0.0008, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_loss": 0.8539571166038513, | |
| "eval_runtime": 1235.3917, | |
| "eval_samples_per_second": 4.973, | |
| "eval_steps_per_second": 0.498, | |
| "eval_wer": 52.97009042429863, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 5.026315789473684e-08, | |
| "loss": 0.0002, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 5e-08, | |
| "loss": 0.0004, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.973684210526315e-08, | |
| "loss": 0.0002, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 4.947368421052631e-08, | |
| "loss": 0.0002, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_loss": 0.8545138239860535, | |
| "eval_runtime": 1232.7761, | |
| "eval_samples_per_second": 4.983, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 52.8124275446325, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.921052631578947e-08, | |
| "loss": 0.0008, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 4.894736842105263e-08, | |
| "loss": 0.0002, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 4.868421052631579e-08, | |
| "loss": 0.0335, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 4.8421052631578944e-08, | |
| "loss": 0.0002, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "eval_loss": 0.8554033041000366, | |
| "eval_runtime": 1229.4133, | |
| "eval_samples_per_second": 4.997, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 53.09297472756782, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 4.81578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 4.789473684210526e-08, | |
| "loss": 0.0004, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 4.763157894736842e-08, | |
| "loss": 0.0005, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 4.736842105263157e-08, | |
| "loss": 0.0003, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "eval_loss": 0.8557314276695251, | |
| "eval_runtime": 1225.1241, | |
| "eval_samples_per_second": 5.014, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.85416183630883, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 4.7105263157894735e-08, | |
| "loss": 0.0004, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 4.684210526315789e-08, | |
| "loss": 0.0367, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 4.657894736842105e-08, | |
| "loss": 0.0002, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 4.631578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "eval_loss": 0.856380045413971, | |
| "eval_runtime": 1232.385, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 53.04892186413169, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 4.6052631578947364e-08, | |
| "loss": 0.0005, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 4.578947368421052e-08, | |
| "loss": 0.0002, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 4.552631578947368e-08, | |
| "loss": 0.0004, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 4.5263157894736844e-08, | |
| "loss": 0.0003, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "eval_loss": 0.8556529879570007, | |
| "eval_runtime": 1226.5022, | |
| "eval_samples_per_second": 5.009, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.75214467887781, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 4.5e-08, | |
| "loss": 0.0002, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.4736842105263155e-08, | |
| "loss": 0.0003, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.447368421052631e-08, | |
| "loss": 0.0005, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.421052631578947e-08, | |
| "loss": 0.0342, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "eval_loss": 0.8558121919631958, | |
| "eval_runtime": 1230.3763, | |
| "eval_samples_per_second": 4.993, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.369580338511476, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 4.394736842105263e-08, | |
| "loss": 0.0002, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 4.368421052631579e-08, | |
| "loss": 0.0004, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.3421052631578946e-08, | |
| "loss": 0.0022, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 4.31578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "eval_loss": 0.8560585975646973, | |
| "eval_runtime": 1228.3933, | |
| "eval_samples_per_second": 5.001, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.536517505216786, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.2894736842105263e-08, | |
| "loss": 0.0002, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 4.263157894736842e-08, | |
| "loss": 0.0002, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 4.2368421052631575e-08, | |
| "loss": 0.0003, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 4.210526315789473e-08, | |
| "loss": 0.0002, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "eval_loss": 0.8568394184112549, | |
| "eval_runtime": 1223.7352, | |
| "eval_samples_per_second": 5.02, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 52.11221887317412, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 4.184210526315789e-08, | |
| "loss": 0.0002, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 4.1578947368421054e-08, | |
| "loss": 0.0003, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 4.131578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 4.1052631578947365e-08, | |
| "loss": 0.0005, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "eval_loss": 0.8579289317131042, | |
| "eval_runtime": 1226.8535, | |
| "eval_samples_per_second": 5.007, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.253651750521676, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 4.078947368421052e-08, | |
| "loss": 0.0003, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 4.052631578947368e-08, | |
| "loss": 0.0003, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 4.026315789473684e-08, | |
| "loss": 0.0006, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 4e-08, | |
| "loss": 0.0003, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 0.8579568266868591, | |
| "eval_runtime": 1221.3459, | |
| "eval_samples_per_second": 5.03, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.005564572223506, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 3.9736842105263156e-08, | |
| "loss": 0.001, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 3.947368421052631e-08, | |
| "loss": 0.0002, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 3.9210526315789474e-08, | |
| "loss": 0.0002, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.894736842105263e-08, | |
| "loss": 0.0002, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "eval_loss": 0.8575696349143982, | |
| "eval_runtime": 1230.0823, | |
| "eval_samples_per_second": 4.994, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.378854625550666, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 3.8684210526315785e-08, | |
| "loss": 0.0004, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 3.842105263157894e-08, | |
| "loss": 0.0002, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 3.81578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 3.7894736842105265e-08, | |
| "loss": 0.0318, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_loss": 0.8580388426780701, | |
| "eval_runtime": 1223.844, | |
| "eval_samples_per_second": 5.019, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 52.339438905634125, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 3.763157894736842e-08, | |
| "loss": 0.0002, | |
| "step": 6425 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 3.7368421052631576e-08, | |
| "loss": 0.0002, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 3.710526315789473e-08, | |
| "loss": 0.0308, | |
| "step": 6475 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 3.6842105263157894e-08, | |
| "loss": 0.0002, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "eval_loss": 0.8583086133003235, | |
| "eval_runtime": 1224.9878, | |
| "eval_samples_per_second": 5.015, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.52260607465801, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 3.6578947368421056e-08, | |
| "loss": 0.0002, | |
| "step": 6525 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 3.631578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 3.605263157894737e-08, | |
| "loss": 0.0004, | |
| "step": 6575 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 3.578947368421052e-08, | |
| "loss": 0.0018, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "eval_loss": 0.8587020635604858, | |
| "eval_runtime": 1224.4026, | |
| "eval_samples_per_second": 5.017, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.566658938094136, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 3.5526315789473685e-08, | |
| "loss": 0.0003, | |
| "step": 6625 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 3.526315789473684e-08, | |
| "loss": 0.0002, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.4999999999999996e-08, | |
| "loss": 0.0002, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 3.473684210526316e-08, | |
| "loss": 0.0002, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "eval_loss": 0.8588802814483643, | |
| "eval_runtime": 1223.8055, | |
| "eval_samples_per_second": 5.02, | |
| "eval_steps_per_second": 0.503, | |
| "eval_wer": 52.51796893113841, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 3.4473684210526313e-08, | |
| "loss": 0.0007, | |
| "step": 6725 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 3.4210526315789476e-08, | |
| "loss": 0.0002, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.394736842105263e-08, | |
| "loss": 0.0002, | |
| "step": 6775 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 3.368421052631579e-08, | |
| "loss": 0.0003, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "eval_loss": 0.8594960570335388, | |
| "eval_runtime": 1219.4743, | |
| "eval_samples_per_second": 5.037, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.59911894273128, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 3.342105263157894e-08, | |
| "loss": 0.0343, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 3.3157894736842104e-08, | |
| "loss": 0.0003, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 3.2894736842105267e-08, | |
| "loss": 0.0002, | |
| "step": 6875 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 3.263157894736842e-08, | |
| "loss": 0.0002, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "eval_loss": 0.8599104285240173, | |
| "eval_runtime": 1218.918, | |
| "eval_samples_per_second": 5.04, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 52.434500347785765, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 3.236842105263158e-08, | |
| "loss": 0.0003, | |
| "step": 6925 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 3.210526315789473e-08, | |
| "loss": 0.0002, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 3.1842105263157895e-08, | |
| "loss": 0.0002, | |
| "step": 6975 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 3.157894736842105e-08, | |
| "loss": 0.0004, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "eval_loss": 0.8596522212028503, | |
| "eval_runtime": 1224.2819, | |
| "eval_samples_per_second": 5.018, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.59911894273128, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 3.1315789473684206e-08, | |
| "loss": 0.0002, | |
| "step": 7025 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 3.105263157894737e-08, | |
| "loss": 0.0002, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 3.0789473684210524e-08, | |
| "loss": 0.0002, | |
| "step": 7075 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 3.0526315789473686e-08, | |
| "loss": 0.0002, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "eval_loss": 0.8602133989334106, | |
| "eval_runtime": 1218.6805, | |
| "eval_samples_per_second": 5.041, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 52.59448179921169, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 3.026315789473684e-08, | |
| "loss": 0.0001, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 3e-08, | |
| "loss": 0.0002, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 2.9736842105263156e-08, | |
| "loss": 0.0339, | |
| "step": 7175 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 2.9473684210526312e-08, | |
| "loss": 0.0003, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "eval_loss": 0.8607735633850098, | |
| "eval_runtime": 1229.6706, | |
| "eval_samples_per_second": 4.996, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.59448179921169, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 2.9210526315789474e-08, | |
| "loss": 0.0007, | |
| "step": 7225 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 2.8947368421052633e-08, | |
| "loss": 0.0002, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 2.8684210526315788e-08, | |
| "loss": 0.0003, | |
| "step": 7275 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 2.8421052631578947e-08, | |
| "loss": 0.0002, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "eval_loss": 0.8609676361083984, | |
| "eval_runtime": 1219.0, | |
| "eval_samples_per_second": 5.039, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 52.77069325295618, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 2.8157894736842103e-08, | |
| "loss": 0.0002, | |
| "step": 7325 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 2.7894736842105258e-08, | |
| "loss": 0.0002, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 2.7631578947368424e-08, | |
| "loss": 0.0003, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 2.736842105263158e-08, | |
| "loss": 0.0002, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "eval_loss": 0.8615851998329163, | |
| "eval_runtime": 1219.8009, | |
| "eval_samples_per_second": 5.036, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 52.65476466496638, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 2.7105263157894738e-08, | |
| "loss": 0.0002, | |
| "step": 7425 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 2.6842105263157894e-08, | |
| "loss": 0.0002, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 2.6578947368421052e-08, | |
| "loss": 0.0002, | |
| "step": 7475 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 2.6315789473684208e-08, | |
| "loss": 0.0016, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "eval_loss": 0.8613052368164062, | |
| "eval_runtime": 1224.3464, | |
| "eval_samples_per_second": 5.017, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.66172038024577, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 2.6052631578947363e-08, | |
| "loss": 0.0373, | |
| "step": 7525 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 2.578947368421053e-08, | |
| "loss": 0.0001, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 2.5526315789473684e-08, | |
| "loss": 0.0003, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 2.5263157894736843e-08, | |
| "loss": 0.0002, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "eval_loss": 0.861556887626648, | |
| "eval_runtime": 1218.4348, | |
| "eval_samples_per_second": 5.042, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 52.645490377927196, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 2.5e-08, | |
| "loss": 0.0002, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 2.4736842105263154e-08, | |
| "loss": 0.0002, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 2.4473684210526317e-08, | |
| "loss": 0.0002, | |
| "step": 7675 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 2.4210526315789472e-08, | |
| "loss": 0.0003, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.8617716431617737, | |
| "eval_runtime": 1225.7627, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.66635752376536, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 2.394736842105263e-08, | |
| "loss": 0.0002, | |
| "step": 7725 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 2.3684210526315786e-08, | |
| "loss": 0.0002, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 2.3421052631578945e-08, | |
| "loss": 0.0003, | |
| "step": 7775 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 2.3157894736842104e-08, | |
| "loss": 0.0002, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "eval_loss": 0.8619219660758972, | |
| "eval_runtime": 1225.7548, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.71504753072107, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 2.289473684210526e-08, | |
| "loss": 0.0002, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 2.2631578947368422e-08, | |
| "loss": 0.0003, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 2.2368421052631577e-08, | |
| "loss": 0.0002, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 2.2105263157894736e-08, | |
| "loss": 0.0003, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "eval_loss": 0.8622960448265076, | |
| "eval_runtime": 1223.9802, | |
| "eval_samples_per_second": 5.019, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.56897750985393, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 2.1842105263157895e-08, | |
| "loss": 0.0002, | |
| "step": 7925 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 2.157894736842105e-08, | |
| "loss": 0.0002, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 2.131578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 7975 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 2.1052631578947365e-08, | |
| "loss": 0.0002, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "eval_loss": 0.8626374006271362, | |
| "eval_runtime": 1229.0871, | |
| "eval_samples_per_second": 4.998, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.56897750985393, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 2.0789473684210527e-08, | |
| "loss": 0.0002, | |
| "step": 8025 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 2.0526315789473683e-08, | |
| "loss": 0.0344, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 2.026315789473684e-08, | |
| "loss": 0.0002, | |
| "step": 8075 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 2e-08, | |
| "loss": 0.0002, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "eval_loss": 0.8625970482826233, | |
| "eval_runtime": 1226.9309, | |
| "eval_samples_per_second": 5.007, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.543473220496175, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 1.9736842105263156e-08, | |
| "loss": 0.0016, | |
| "step": 8125 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 1.9473684210526315e-08, | |
| "loss": 0.0001, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 1.921052631578947e-08, | |
| "loss": 0.0002, | |
| "step": 8175 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 1.8947368421052632e-08, | |
| "loss": 0.0002, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "eval_loss": 0.8626481294631958, | |
| "eval_runtime": 1228.3849, | |
| "eval_samples_per_second": 5.001, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.408996058428, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 1.8684210526315788e-08, | |
| "loss": 0.0321, | |
| "step": 8225 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.8421052631578947e-08, | |
| "loss": 0.0006, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 1.8157894736842106e-08, | |
| "loss": 0.0002, | |
| "step": 8275 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 1.789473684210526e-08, | |
| "loss": 0.0002, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "eval_loss": 0.8629574179649353, | |
| "eval_runtime": 1224.7389, | |
| "eval_samples_per_second": 5.016, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.376536053790865, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 1.763157894736842e-08, | |
| "loss": 0.0002, | |
| "step": 8325 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.736842105263158e-08, | |
| "loss": 0.0002, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.7105263157894738e-08, | |
| "loss": 0.0002, | |
| "step": 8375 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 1.6842105263157893e-08, | |
| "loss": 0.0002, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "eval_loss": 0.863264799118042, | |
| "eval_runtime": 1235.2138, | |
| "eval_samples_per_second": 4.973, | |
| "eval_steps_per_second": 0.498, | |
| "eval_wer": 52.369580338511476, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 1.6578947368421052e-08, | |
| "loss": 0.0002, | |
| "step": 8425 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 1.631578947368421e-08, | |
| "loss": 0.0002, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 1.6052631578947367e-08, | |
| "loss": 0.0002, | |
| "step": 8475 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 1.5789473684210525e-08, | |
| "loss": 0.0001, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "eval_loss": 0.8635631203651428, | |
| "eval_runtime": 1228.5668, | |
| "eval_samples_per_second": 5.0, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.33480176211454, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 1.5526315789473684e-08, | |
| "loss": 0.0002, | |
| "step": 8525 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 1.5263157894736843e-08, | |
| "loss": 0.0002, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 1.5e-08, | |
| "loss": 0.0002, | |
| "step": 8575 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 1.4736842105263156e-08, | |
| "loss": 0.0003, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "eval_loss": 0.8637988567352295, | |
| "eval_runtime": 1225.2242, | |
| "eval_samples_per_second": 5.014, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.20264317180616, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 1.4473684210526316e-08, | |
| "loss": 0.0002, | |
| "step": 8625 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 1.4210526315789474e-08, | |
| "loss": 0.0004, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 1.3947368421052629e-08, | |
| "loss": 0.0002, | |
| "step": 8675 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 1.368421052631579e-08, | |
| "loss": 0.0002, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "eval_loss": 0.8641210198402405, | |
| "eval_runtime": 1228.2279, | |
| "eval_samples_per_second": 5.002, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.20959888708555, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 1.3421052631578947e-08, | |
| "loss": 0.0016, | |
| "step": 8725 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 1.3157894736842104e-08, | |
| "loss": 0.0003, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 1.2894736842105264e-08, | |
| "loss": 0.0001, | |
| "step": 8775 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 1.2631578947368422e-08, | |
| "loss": 0.0002, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "eval_loss": 0.8640812039375305, | |
| "eval_runtime": 1230.5661, | |
| "eval_samples_per_second": 4.992, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.21887317412474, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 1.2368421052631577e-08, | |
| "loss": 0.0002, | |
| "step": 8825 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 1.2105263157894736e-08, | |
| "loss": 0.0679, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 1.1842105263157893e-08, | |
| "loss": 0.0002, | |
| "step": 8875 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 1.1578947368421052e-08, | |
| "loss": 0.0002, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "eval_loss": 0.8640047907829285, | |
| "eval_runtime": 1231.6516, | |
| "eval_samples_per_second": 4.988, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 51.99165314166474, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 1.1315789473684211e-08, | |
| "loss": 0.0002, | |
| "step": 8925 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 1.1052631578947368e-08, | |
| "loss": 0.0002, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 1.0789473684210525e-08, | |
| "loss": 0.0002, | |
| "step": 8975 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.0526315789473683e-08, | |
| "loss": 0.0002, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_loss": 0.864069402217865, | |
| "eval_runtime": 1231.2207, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.00092742870391, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 1.0263157894736841e-08, | |
| "loss": 0.0002, | |
| "step": 9025 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 1e-08, | |
| "loss": 0.0002, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 9.736842105263157e-09, | |
| "loss": 0.0002, | |
| "step": 9075 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 9.473684210526316e-09, | |
| "loss": 0.0004, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "eval_loss": 0.8642098307609558, | |
| "eval_runtime": 1231.3923, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 52.14236030605147, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 9.210526315789473e-09, | |
| "loss": 0.0002, | |
| "step": 9125 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 8.94736842105263e-09, | |
| "loss": 0.0002, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 8.68421052631579e-09, | |
| "loss": 0.0002, | |
| "step": 9175 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 8.421052631578947e-09, | |
| "loss": 0.0002, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "eval_loss": 0.8643378615379333, | |
| "eval_runtime": 1237.8854, | |
| "eval_samples_per_second": 4.962, | |
| "eval_steps_per_second": 0.497, | |
| "eval_wer": 52.16322745188964, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 8.157894736842106e-09, | |
| "loss": 0.0002, | |
| "step": 9225 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 7.894736842105263e-09, | |
| "loss": 0.0015, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "learning_rate": 7.631578947368422e-09, | |
| "loss": 0.0002, | |
| "step": 9275 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 7.368421052631578e-09, | |
| "loss": 0.0002, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "eval_loss": 0.8643071055412292, | |
| "eval_runtime": 1231.1848, | |
| "eval_samples_per_second": 4.99, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.13076744725249, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 7.105263157894737e-09, | |
| "loss": 0.0002, | |
| "step": 9325 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 6.842105263157895e-09, | |
| "loss": 0.0002, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 6.578947368421052e-09, | |
| "loss": 0.0003, | |
| "step": 9375 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 6.315789473684211e-09, | |
| "loss": 0.0323, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "eval_loss": 0.8643560409545898, | |
| "eval_runtime": 1230.0692, | |
| "eval_samples_per_second": 4.994, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.14931602133086, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 6.052631578947368e-09, | |
| "loss": 0.0002, | |
| "step": 9425 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 5.789473684210526e-09, | |
| "loss": 0.0002, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 5.526315789473684e-09, | |
| "loss": 0.0002, | |
| "step": 9475 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 5.263157894736841e-09, | |
| "loss": 0.0311, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "eval_loss": 0.8644668459892273, | |
| "eval_runtime": 1230.2998, | |
| "eval_samples_per_second": 4.993, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.14236030605147, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 5e-09, | |
| "loss": 0.0002, | |
| "step": 9525 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 4.736842105263158e-09, | |
| "loss": 0.0001, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "learning_rate": 4.473684210526315e-09, | |
| "loss": 0.0003, | |
| "step": 9575 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 4.210526315789473e-09, | |
| "loss": 0.0002, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_loss": 0.8644796013832092, | |
| "eval_runtime": 1230.811, | |
| "eval_samples_per_second": 4.991, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 52.13772316253188, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.947368421052631e-09, | |
| "loss": 0.0002, | |
| "step": 9625 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 3.684210526315789e-09, | |
| "loss": 0.0002, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 3.4210526315789474e-09, | |
| "loss": 0.0002, | |
| "step": 9675 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 3.1578947368421054e-09, | |
| "loss": 0.0001, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "eval_loss": 0.864521861076355, | |
| "eval_runtime": 1231.7778, | |
| "eval_samples_per_second": 4.987, | |
| "eval_steps_per_second": 0.499, | |
| "eval_wer": 52.13772316253188, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 2.894736842105263e-09, | |
| "loss": 0.0002, | |
| "step": 9725 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 2.6315789473684206e-09, | |
| "loss": 0.0313, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 2.368421052631579e-09, | |
| "loss": 0.0001, | |
| "step": 9775 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 2.1052631578947367e-09, | |
| "loss": 0.0002, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "eval_loss": 0.8645275235176086, | |
| "eval_runtime": 1227.816, | |
| "eval_samples_per_second": 5.003, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.13772316253188, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 1.8421052631578945e-09, | |
| "loss": 0.0002, | |
| "step": 9825 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 1.5789473684210527e-09, | |
| "loss": 0.0002, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 1.3157894736842103e-09, | |
| "loss": 0.0002, | |
| "step": 9875 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 1.0526315789473683e-09, | |
| "loss": 0.0002, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "eval_loss": 0.8645429015159607, | |
| "eval_runtime": 1225.789, | |
| "eval_samples_per_second": 5.011, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 52.13772316253188, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 7.894736842105264e-10, | |
| "loss": 0.0002, | |
| "step": 9925 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 5.263157894736842e-10, | |
| "loss": 0.0003, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 2.631578947368421e-10, | |
| "loss": 0.0002, | |
| "step": 9975 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 0.0, | |
| "loss": 0.0002, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "eval_loss": 0.8645457029342651, | |
| "eval_runtime": 1226.3964, | |
| "eval_samples_per_second": 5.009, | |
| "eval_steps_per_second": 0.501, | |
| "eval_wer": 52.14004173429168, | |
| "step": 10000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 10000, | |
| "num_train_epochs": 16, | |
| "save_steps": 100, | |
| "total_flos": 1.15412516222976e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |