| { | |
| "best_metric": 141.1764705882353, | |
| "best_model_checkpoint": "./whisper-medium-v2-amet/checkpoint-1000", | |
| "epoch": 3000.0, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 2.8559, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 1.9972, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.42e-06, | |
| "loss": 0.8333, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 0.0194, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 3.8540303707122803, | |
| "eval_runtime": 172.9892, | |
| "eval_samples_per_second": 0.289, | |
| "eval_steps_per_second": 0.023, | |
| "eval_wer": 147.99465240641712, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 2.42e-06, | |
| "loss": 0.0002, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.0001, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.0001, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "eval_loss": 4.147902011871338, | |
| "eval_runtime": 173.0433, | |
| "eval_samples_per_second": 0.289, | |
| "eval_steps_per_second": 0.023, | |
| "eval_wer": 148.1283422459893, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 225.0, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.0001, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.0001, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 275.0, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.0001, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "eval_loss": 4.183959007263184, | |
| "eval_runtime": 212.6643, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 150.53475935828877, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 325.0, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.0001, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 350.0, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.0001, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 375.0, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.0001, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "eval_loss": 4.333920001983643, | |
| "eval_runtime": 205.1394, | |
| "eval_samples_per_second": 0.244, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 177.94117647058823, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 425.0, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.0001, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 450.0, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 475.0, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.0001, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "eval_loss": 4.583085536956787, | |
| "eval_runtime": 212.5309, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 151.06951871657753, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 525.0, | |
| "learning_rate": 9.916000000000001e-06, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 550.0, | |
| "learning_rate": 9.816e-06, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 575.0, | |
| "learning_rate": 9.716000000000002e-06, | |
| "loss": 0.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 600.0, | |
| "learning_rate": 9.616e-06, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 600.0, | |
| "eval_loss": 4.931729793548584, | |
| "eval_runtime": 212.8362, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 164.0374331550802, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 625.0, | |
| "learning_rate": 9.516e-06, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 650.0, | |
| "learning_rate": 9.416000000000001e-06, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 675.0, | |
| "learning_rate": 9.316e-06, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 700.0, | |
| "learning_rate": 9.216000000000001e-06, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 700.0, | |
| "eval_loss": 5.303104877471924, | |
| "eval_runtime": 204.8283, | |
| "eval_samples_per_second": 0.244, | |
| "eval_steps_per_second": 0.02, | |
| "eval_wer": 141.0427807486631, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 725.0, | |
| "learning_rate": 9.116e-06, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 750.0, | |
| "learning_rate": 9.016e-06, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 775.0, | |
| "learning_rate": 8.916e-06, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 800.0, | |
| "learning_rate": 8.816000000000002e-06, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 800.0, | |
| "eval_loss": 5.658377170562744, | |
| "eval_runtime": 204.6203, | |
| "eval_samples_per_second": 0.244, | |
| "eval_steps_per_second": 0.02, | |
| "eval_wer": 122.32620320855614, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 825.0, | |
| "learning_rate": 8.716000000000001e-06, | |
| "loss": 0.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 850.0, | |
| "learning_rate": 8.616000000000002e-06, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 875.0, | |
| "learning_rate": 8.516000000000001e-06, | |
| "loss": 0.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 900.0, | |
| "learning_rate": 8.416e-06, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 900.0, | |
| "eval_loss": 5.971085071563721, | |
| "eval_runtime": 213.3134, | |
| "eval_samples_per_second": 0.234, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 157.4866310160428, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 925.0, | |
| "learning_rate": 8.316000000000001e-06, | |
| "loss": 0.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 950.0, | |
| "learning_rate": 8.216e-06, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 975.0, | |
| "learning_rate": 8.116e-06, | |
| "loss": 0.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1000.0, | |
| "learning_rate": 8.016e-06, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1000.0, | |
| "eval_loss": 6.246512413024902, | |
| "eval_runtime": 213.4328, | |
| "eval_samples_per_second": 0.234, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 141.1764705882353, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1025.0, | |
| "learning_rate": 7.916e-06, | |
| "loss": 0.0, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1050.0, | |
| "learning_rate": 7.816000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1075.0, | |
| "learning_rate": 7.716e-06, | |
| "loss": 0.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1100.0, | |
| "learning_rate": 7.616000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1100.0, | |
| "eval_loss": 6.483173847198486, | |
| "eval_runtime": 213.8254, | |
| "eval_samples_per_second": 0.234, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 169.6524064171123, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1125.0, | |
| "learning_rate": 7.516000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1150.0, | |
| "learning_rate": 7.416000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1175.0, | |
| "learning_rate": 7.316000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1200.0, | |
| "learning_rate": 7.216000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1200.0, | |
| "eval_loss": 6.6890459060668945, | |
| "eval_runtime": 209.6765, | |
| "eval_samples_per_second": 0.238, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 155.0802139037433, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1225.0, | |
| "learning_rate": 7.116000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1250.0, | |
| "learning_rate": 7.016e-06, | |
| "loss": 0.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1275.0, | |
| "learning_rate": 6.916e-06, | |
| "loss": 0.0, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1300.0, | |
| "learning_rate": 6.8160000000000005e-06, | |
| "loss": 0.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1300.0, | |
| "eval_loss": 6.867943286895752, | |
| "eval_runtime": 209.9316, | |
| "eval_samples_per_second": 0.238, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 159.75935828877004, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1325.0, | |
| "learning_rate": 6.716000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1350.0, | |
| "learning_rate": 6.616e-06, | |
| "loss": 0.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1375.0, | |
| "learning_rate": 6.516e-06, | |
| "loss": 0.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1400.0, | |
| "learning_rate": 6.416e-06, | |
| "loss": 0.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1400.0, | |
| "eval_loss": 7.025048732757568, | |
| "eval_runtime": 212.7993, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 155.0802139037433, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1425.0, | |
| "learning_rate": 6.316000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1450.0, | |
| "learning_rate": 6.216000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1475.0, | |
| "learning_rate": 6.116000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1500.0, | |
| "learning_rate": 6.0160000000000005e-06, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1500.0, | |
| "eval_loss": 7.161492347717285, | |
| "eval_runtime": 212.8178, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 146.2566844919786, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1525.0, | |
| "learning_rate": 5.916000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1550.0, | |
| "learning_rate": 5.816000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1575.0, | |
| "learning_rate": 5.716000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1600.0, | |
| "learning_rate": 5.616e-06, | |
| "loss": 0.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1600.0, | |
| "eval_loss": 7.2876811027526855, | |
| "eval_runtime": 212.9353, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 143.04812834224597, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1625.0, | |
| "learning_rate": 5.516e-06, | |
| "loss": 0.0, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1650.0, | |
| "learning_rate": 5.416e-06, | |
| "loss": 0.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1675.0, | |
| "learning_rate": 5.3160000000000004e-06, | |
| "loss": 0.0, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1700.0, | |
| "learning_rate": 5.216e-06, | |
| "loss": 0.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1700.0, | |
| "eval_loss": 7.3986992835998535, | |
| "eval_runtime": 212.9015, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 148.52941176470588, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1725.0, | |
| "learning_rate": 5.116000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1750.0, | |
| "learning_rate": 5.016000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1775.0, | |
| "learning_rate": 4.916e-06, | |
| "loss": 0.0, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1800.0, | |
| "learning_rate": 4.816e-06, | |
| "loss": 0.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1800.0, | |
| "eval_loss": 7.501037120819092, | |
| "eval_runtime": 213.1608, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 142.5133689839572, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1825.0, | |
| "learning_rate": 4.716e-06, | |
| "loss": 0.0, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1850.0, | |
| "learning_rate": 4.616e-06, | |
| "loss": 0.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1875.0, | |
| "learning_rate": 4.5160000000000005e-06, | |
| "loss": 0.0, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1900.0, | |
| "learning_rate": 4.416000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1900.0, | |
| "eval_loss": 7.584920883178711, | |
| "eval_runtime": 213.8853, | |
| "eval_samples_per_second": 0.234, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 136.76470588235296, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1925.0, | |
| "learning_rate": 4.316e-06, | |
| "loss": 0.0, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1950.0, | |
| "learning_rate": 4.216e-06, | |
| "loss": 0.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1975.0, | |
| "learning_rate": 4.116000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2000.0, | |
| "learning_rate": 4.016e-06, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2000.0, | |
| "eval_loss": 7.668895244598389, | |
| "eval_runtime": 212.6893, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 148.26203208556151, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2025.0, | |
| "learning_rate": 3.916e-06, | |
| "loss": 0.0, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2050.0, | |
| "learning_rate": 3.816e-06, | |
| "loss": 0.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2075.0, | |
| "learning_rate": 3.716e-06, | |
| "loss": 0.0, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2100.0, | |
| "learning_rate": 3.616e-06, | |
| "loss": 0.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2100.0, | |
| "eval_loss": 7.695452690124512, | |
| "eval_runtime": 213.8269, | |
| "eval_samples_per_second": 0.234, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 165.37433155080214, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2125.0, | |
| "learning_rate": 3.5160000000000007e-06, | |
| "loss": 0.0, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2150.0, | |
| "learning_rate": 3.4160000000000004e-06, | |
| "loss": 0.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2175.0, | |
| "learning_rate": 3.3160000000000005e-06, | |
| "loss": 0.0, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2200.0, | |
| "learning_rate": 3.216e-06, | |
| "loss": 0.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2200.0, | |
| "eval_loss": 7.724720001220703, | |
| "eval_runtime": 213.0213, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 162.96791443850267, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2225.0, | |
| "learning_rate": 3.1160000000000003e-06, | |
| "loss": 0.0, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2250.0, | |
| "learning_rate": 3.016e-06, | |
| "loss": 0.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2275.0, | |
| "learning_rate": 2.9160000000000005e-06, | |
| "loss": 0.0, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2300.0, | |
| "learning_rate": 2.8160000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2300.0, | |
| "eval_loss": 7.755704402923584, | |
| "eval_runtime": 212.9136, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 161.63101604278074, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2325.0, | |
| "learning_rate": 2.7160000000000003e-06, | |
| "loss": 0.0, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2350.0, | |
| "learning_rate": 2.616e-06, | |
| "loss": 0.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2375.0, | |
| "learning_rate": 2.516e-06, | |
| "loss": 0.0, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2400.0, | |
| "learning_rate": 2.4160000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2400.0, | |
| "eval_loss": 7.784246444702148, | |
| "eval_runtime": 213.1347, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 162.29946524064172, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2425.0, | |
| "learning_rate": 2.3160000000000004e-06, | |
| "loss": 0.0, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 2450.0, | |
| "learning_rate": 2.216e-06, | |
| "loss": 0.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2475.0, | |
| "learning_rate": 2.116e-06, | |
| "loss": 0.0, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2500.0, | |
| "learning_rate": 2.0160000000000003e-06, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2500.0, | |
| "eval_loss": 7.807443141937256, | |
| "eval_runtime": 212.982, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 150.93582887700535, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2525.0, | |
| "learning_rate": 1.916e-06, | |
| "loss": 0.0, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 2550.0, | |
| "learning_rate": 1.8160000000000003e-06, | |
| "loss": 0.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2575.0, | |
| "learning_rate": 1.7160000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 2600.0, | |
| "learning_rate": 1.616e-06, | |
| "loss": 0.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2600.0, | |
| "eval_loss": 7.8286895751953125, | |
| "eval_runtime": 213.1069, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 154.81283422459893, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2625.0, | |
| "learning_rate": 1.5160000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2650.0, | |
| "learning_rate": 1.416e-06, | |
| "loss": 0.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2675.0, | |
| "learning_rate": 1.316e-06, | |
| "loss": 0.0, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2700.0, | |
| "learning_rate": 1.216e-06, | |
| "loss": 0.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2700.0, | |
| "eval_loss": 7.843414783477783, | |
| "eval_runtime": 212.8223, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 155.4812834224599, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2725.0, | |
| "learning_rate": 1.1160000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2750.0, | |
| "learning_rate": 1.016e-06, | |
| "loss": 0.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2775.0, | |
| "learning_rate": 9.160000000000001e-07, | |
| "loss": 0.0, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2800.0, | |
| "learning_rate": 8.160000000000001e-07, | |
| "loss": 0.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2800.0, | |
| "eval_loss": 7.856691837310791, | |
| "eval_runtime": 212.6712, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 154.41176470588235, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2825.0, | |
| "learning_rate": 7.16e-07, | |
| "loss": 0.0, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2850.0, | |
| "learning_rate": 6.160000000000001e-07, | |
| "loss": 0.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2875.0, | |
| "learning_rate": 5.16e-07, | |
| "loss": 0.0, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2900.0, | |
| "learning_rate": 4.16e-07, | |
| "loss": 0.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2900.0, | |
| "eval_loss": 7.863497257232666, | |
| "eval_runtime": 212.9291, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 154.41176470588235, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2925.0, | |
| "learning_rate": 3.160000000000001e-07, | |
| "loss": 0.0, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2950.0, | |
| "learning_rate": 2.1600000000000003e-07, | |
| "loss": 0.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2975.0, | |
| "learning_rate": 1.16e-07, | |
| "loss": 0.0, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 3000.0, | |
| "learning_rate": 1.6e-08, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3000.0, | |
| "eval_loss": 7.86700439453125, | |
| "eval_runtime": 212.9038, | |
| "eval_samples_per_second": 0.235, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 154.41176470588235, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3000.0, | |
| "step": 3000, | |
| "total_flos": 3.06181472256e+18, | |
| "train_loss": 0.047578999360693465, | |
| "train_runtime": 7446.2425, | |
| "train_samples_per_second": 12.892, | |
| "train_steps_per_second": 0.403 | |
| } | |
| ], | |
| "max_steps": 3000, | |
| "num_train_epochs": 3000, | |
| "total_flos": 3.06181472256e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |