| { | |
| "best_metric": 45.965834862992175, | |
| "best_model_checkpoint": "/media/makhataei/Backups/Whisper-Small-Common-Voice/checkpoint-6200", | |
| "epoch": 24.71042471042471, | |
| "eval_steps": 100, | |
| "global_step": 6400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 3.1025, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.3525, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.976884422110554e-06, | |
| "loss": 0.9564, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.95175879396985e-06, | |
| "loss": 0.7495, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.860159158706665, | |
| "eval_runtime": 1426.2695, | |
| "eval_samples_per_second": 6.062, | |
| "eval_steps_per_second": 0.606, | |
| "eval_wer": 58.07742554282218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.926633165829147e-06, | |
| "loss": 0.5073, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.901507537688444e-06, | |
| "loss": 0.3749, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.87638190954774e-06, | |
| "loss": 0.3247, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.851256281407035e-06, | |
| "loss": 0.3059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.5538379549980164, | |
| "eval_runtime": 1589.2333, | |
| "eval_samples_per_second": 5.44, | |
| "eval_steps_per_second": 0.544, | |
| "eval_wer": 55.22481850804518, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.826130653266333e-06, | |
| "loss": 0.2963, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.80100502512563e-06, | |
| "loss": 0.2882, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.775879396984925e-06, | |
| "loss": 0.2327, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.750753768844222e-06, | |
| "loss": 0.2002, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.5136818885803223, | |
| "eval_runtime": 1646.1357, | |
| "eval_samples_per_second": 5.252, | |
| "eval_steps_per_second": 0.525, | |
| "eval_wer": 52.46151047609599, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.725628140703518e-06, | |
| "loss": 0.1893, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.700502512562815e-06, | |
| "loss": 0.185, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.675376884422111e-06, | |
| "loss": 0.1847, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.650251256281408e-06, | |
| "loss": 0.1798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.5102902054786682, | |
| "eval_runtime": 1650.3734, | |
| "eval_samples_per_second": 5.239, | |
| "eval_steps_per_second": 0.524, | |
| "eval_wer": 51.65781945064576, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.625125628140705e-06, | |
| "loss": 0.1804, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.1807, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.574874371859298e-06, | |
| "loss": 0.1714, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.549748743718595e-06, | |
| "loss": 0.1678, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.48063144087791443, | |
| "eval_runtime": 1482.5018, | |
| "eval_samples_per_second": 5.832, | |
| "eval_steps_per_second": 0.583, | |
| "eval_wer": 46.55123943708554, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.52462311557789e-06, | |
| "loss": 0.1542, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.499497487437188e-06, | |
| "loss": 0.0929, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 9.474371859296483e-06, | |
| "loss": 0.0936, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.44924623115578e-06, | |
| "loss": 0.0932, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.49363330006599426, | |
| "eval_runtime": 1993.4903, | |
| "eval_samples_per_second": 4.337, | |
| "eval_steps_per_second": 0.434, | |
| "eval_wer": 47.49549370772767, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.424120603015076e-06, | |
| "loss": 0.0936, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.398994974874373e-06, | |
| "loss": 0.0955, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.373869346733669e-06, | |
| "loss": 0.0871, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.348743718592966e-06, | |
| "loss": 0.0944, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.5119881629943848, | |
| "eval_runtime": 1791.3192, | |
| "eval_samples_per_second": 4.827, | |
| "eval_steps_per_second": 0.483, | |
| "eval_wer": 48.91600932678474, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.323618090452262e-06, | |
| "loss": 0.0927, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.298492462311557e-06, | |
| "loss": 0.0964, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.273366834170856e-06, | |
| "loss": 0.1038, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 9.248241206030152e-06, | |
| "loss": 0.0493, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.5198288559913635, | |
| "eval_runtime": 1878.4077, | |
| "eval_samples_per_second": 4.603, | |
| "eval_steps_per_second": 0.46, | |
| "eval_wer": 48.26114997271419, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.223115577889447e-06, | |
| "loss": 0.0501, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 9.197989949748744e-06, | |
| "loss": 0.0458, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 9.17286432160804e-06, | |
| "loss": 0.0492, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 9.147738693467337e-06, | |
| "loss": 0.0506, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.5227376222610474, | |
| "eval_runtime": 1759.968, | |
| "eval_samples_per_second": 4.913, | |
| "eval_steps_per_second": 0.491, | |
| "eval_wer": 47.41280944585008, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 9.122613065326634e-06, | |
| "loss": 0.0494, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 9.09748743718593e-06, | |
| "loss": 0.051, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 9.072361809045227e-06, | |
| "loss": 0.0466, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 9.047236180904524e-06, | |
| "loss": 0.0482, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 0.5255833268165588, | |
| "eval_runtime": 1701.3645, | |
| "eval_samples_per_second": 5.082, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 46.94977757933555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 9.02211055276382e-06, | |
| "loss": 0.046, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 8.996984924623117e-06, | |
| "loss": 0.0368, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 8.971859296482412e-06, | |
| "loss": 0.0233, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 8.94673366834171e-06, | |
| "loss": 0.0244, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "eval_loss": 0.5491495132446289, | |
| "eval_runtime": 1619.0836, | |
| "eval_samples_per_second": 5.34, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 46.084900200095916, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 8.921608040201005e-06, | |
| "loss": 0.0258, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 8.896482412060302e-06, | |
| "loss": 0.0248, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 8.8713567839196e-06, | |
| "loss": 0.0241, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 8.846231155778895e-06, | |
| "loss": 0.0272, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 0.5620735883712769, | |
| "eval_runtime": 1837.7585, | |
| "eval_samples_per_second": 4.705, | |
| "eval_steps_per_second": 0.471, | |
| "eval_wer": 46.916703874584506, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 8.821105527638191e-06, | |
| "loss": 0.0258, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 8.795979899497488e-06, | |
| "loss": 0.0237, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 8.770854271356785e-06, | |
| "loss": 0.0266, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 8.745728643216081e-06, | |
| "loss": 0.0246, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_loss": 0.5855526328086853, | |
| "eval_runtime": 1908.9589, | |
| "eval_samples_per_second": 4.529, | |
| "eval_steps_per_second": 0.453, | |
| "eval_wer": 48.80355873063122, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 8.720603015075378e-06, | |
| "loss": 0.0142, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 8.695477386934675e-06, | |
| "loss": 0.014, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 8.67035175879397e-06, | |
| "loss": 0.0126, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 8.645226130653268e-06, | |
| "loss": 0.0159, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.6145116090774536, | |
| "eval_runtime": 1843.4778, | |
| "eval_samples_per_second": 4.69, | |
| "eval_steps_per_second": 0.469, | |
| "eval_wer": 48.30414578889054, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.620100502512564e-06, | |
| "loss": 0.0144, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 8.59497487437186e-06, | |
| "loss": 0.0133, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 8.569849246231156e-06, | |
| "loss": 0.0151, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 8.544723618090453e-06, | |
| "loss": 0.0152, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 0.6177700757980347, | |
| "eval_runtime": 1839.895, | |
| "eval_samples_per_second": 4.699, | |
| "eval_steps_per_second": 0.47, | |
| "eval_wer": 47.756775975260865, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 8.51959798994975e-06, | |
| "loss": 0.014, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 8.494472361809046e-06, | |
| "loss": 0.016, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.469346733668342e-06, | |
| "loss": 0.0092, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 8.444221105527639e-06, | |
| "loss": 0.008, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "eval_loss": 0.6190542578697205, | |
| "eval_runtime": 1730.2546, | |
| "eval_samples_per_second": 4.997, | |
| "eval_steps_per_second": 0.5, | |
| "eval_wer": 48.06105405897041, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 8.419095477386936e-06, | |
| "loss": 0.0079, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 8.393969849246232e-06, | |
| "loss": 0.0087, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 8.368844221105529e-06, | |
| "loss": 0.0082, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 8.343718592964824e-06, | |
| "loss": 0.0077, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 0.6308984160423279, | |
| "eval_runtime": 1686.6544, | |
| "eval_samples_per_second": 5.126, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 46.35941194952953, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 8.318592964824122e-06, | |
| "loss": 0.0076, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 8.293467336683417e-06, | |
| "loss": 0.0095, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 8.268341708542714e-06, | |
| "loss": 0.0087, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 8.24321608040201e-06, | |
| "loss": 0.0097, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "eval_loss": 0.6272400617599487, | |
| "eval_runtime": 1856.6423, | |
| "eval_samples_per_second": 4.657, | |
| "eval_steps_per_second": 0.466, | |
| "eval_wer": 47.9138760728283, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 8.218090452261307e-06, | |
| "loss": 0.009, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 8.192964824120604e-06, | |
| "loss": 0.0053, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 8.1678391959799e-06, | |
| "loss": 0.0051, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 8.142713567839197e-06, | |
| "loss": 0.0056, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 0.6594315767288208, | |
| "eval_runtime": 1711.6251, | |
| "eval_samples_per_second": 5.051, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 46.5562004927982, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 8.117587939698493e-06, | |
| "loss": 0.0056, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 8.09246231155779e-06, | |
| "loss": 0.0058, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 8.067336683417087e-06, | |
| "loss": 0.007, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 8.042211055276382e-06, | |
| "loss": 0.0049, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "eval_loss": 0.6581406593322754, | |
| "eval_runtime": 1917.4042, | |
| "eval_samples_per_second": 4.509, | |
| "eval_steps_per_second": 0.451, | |
| "eval_wer": 47.58313902531792, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 8.01708542713568e-06, | |
| "loss": 0.0064, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 7.991959798994977e-06, | |
| "loss": 0.0055, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 7.966834170854271e-06, | |
| "loss": 0.0055, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 7.941708542713568e-06, | |
| "loss": 0.0042, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "eval_loss": 0.695335865020752, | |
| "eval_runtime": 1836.7482, | |
| "eval_samples_per_second": 4.707, | |
| "eval_steps_per_second": 0.471, | |
| "eval_wer": 48.092474078483896, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 7.916582914572865e-06, | |
| "loss": 0.004, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 7.891457286432161e-06, | |
| "loss": 0.0046, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 7.866331658291458e-06, | |
| "loss": 0.004, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.841206030150755e-06, | |
| "loss": 0.0038, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "eval_loss": 0.6856936812400818, | |
| "eval_runtime": 1910.3433, | |
| "eval_samples_per_second": 4.526, | |
| "eval_steps_per_second": 0.453, | |
| "eval_wer": 48.371946883630166, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 7.816080402010051e-06, | |
| "loss": 0.0036, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 7.790954773869348e-06, | |
| "loss": 0.0038, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 7.765829145728644e-06, | |
| "loss": 0.0033, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 7.740703517587941e-06, | |
| "loss": 0.0033, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "eval_loss": 0.6982905268669128, | |
| "eval_runtime": 1950.8321, | |
| "eval_samples_per_second": 4.432, | |
| "eval_steps_per_second": 0.443, | |
| "eval_wer": 49.69654875890923, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 7.715577889447236e-06, | |
| "loss": 0.0036, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 7.690452261306534e-06, | |
| "loss": 0.0029, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 7.66532663316583e-06, | |
| "loss": 0.0027, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 7.640201005025126e-06, | |
| "loss": 0.003, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "eval_loss": 0.7109295129776001, | |
| "eval_runtime": 1863.5651, | |
| "eval_samples_per_second": 4.639, | |
| "eval_steps_per_second": 0.464, | |
| "eval_wer": 48.11727935704718, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 7.615075376884423e-06, | |
| "loss": 0.003, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 7.589949748743719e-06, | |
| "loss": 0.0025, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 7.564824120603016e-06, | |
| "loss": 0.0027, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 7.5396984924623115e-06, | |
| "loss": 0.0033, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "eval_loss": 0.6899213194847107, | |
| "eval_runtime": 1934.8822, | |
| "eval_samples_per_second": 4.468, | |
| "eval_steps_per_second": 0.447, | |
| "eval_wer": 48.236344694150915, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 7.514572864321609e-06, | |
| "loss": 0.0025, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 7.4894472361809056e-06, | |
| "loss": 0.002, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 7.464321608040201e-06, | |
| "loss": 0.0031, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 7.439195979899499e-06, | |
| "loss": 0.0027, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "eval_loss": 0.7074257135391235, | |
| "eval_runtime": 1945.5025, | |
| "eval_samples_per_second": 4.444, | |
| "eval_steps_per_second": 0.445, | |
| "eval_wer": 48.34052686411668, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 7.4140703517587946e-06, | |
| "loss": 0.0027, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 7.388944723618091e-06, | |
| "loss": 0.0029, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 7.363819095477388e-06, | |
| "loss": 0.0032, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 7.338693467336684e-06, | |
| "loss": 0.0035, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "eval_loss": 0.7017741799354553, | |
| "eval_runtime": 1835.0488, | |
| "eval_samples_per_second": 4.712, | |
| "eval_steps_per_second": 0.471, | |
| "eval_wer": 47.10026293595277, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 7.313567839195981e-06, | |
| "loss": 0.0024, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 7.288442211055277e-06, | |
| "loss": 0.0024, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 7.2633165829145734e-06, | |
| "loss": 0.0031, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 7.23819095477387e-06, | |
| "loss": 0.0026, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "eval_loss": 0.7197884917259216, | |
| "eval_runtime": 1907.1753, | |
| "eval_samples_per_second": 4.533, | |
| "eval_steps_per_second": 0.454, | |
| "eval_wer": 47.12506821451605, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 7.213065326633167e-06, | |
| "loss": 0.0022, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 7.187939698492463e-06, | |
| "loss": 0.0027, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 7.162814070351759e-06, | |
| "loss": 0.0022, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 7.137688442211056e-06, | |
| "loss": 0.0027, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "eval_loss": 0.7459501624107361, | |
| "eval_runtime": 2001.7998, | |
| "eval_samples_per_second": 4.319, | |
| "eval_steps_per_second": 0.432, | |
| "eval_wer": 48.27603313985216, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 7.112562814070353e-06, | |
| "loss": 0.0024, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 7.087437185929649e-06, | |
| "loss": 0.0028, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 7.0623115577889456e-06, | |
| "loss": 0.0022, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 7.037185929648241e-06, | |
| "loss": 0.0023, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "eval_loss": 0.7347891926765442, | |
| "eval_runtime": 1876.4701, | |
| "eval_samples_per_second": 4.608, | |
| "eval_steps_per_second": 0.461, | |
| "eval_wer": 47.71543384432207, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 7.012060301507538e-06, | |
| "loss": 0.0022, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 6.9869346733668354e-06, | |
| "loss": 0.0028, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 6.961809045226131e-06, | |
| "loss": 0.0027, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 6.936683417085428e-06, | |
| "loss": 0.0023, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "eval_loss": 0.7387125492095947, | |
| "eval_runtime": 2084.696, | |
| "eval_samples_per_second": 4.147, | |
| "eval_steps_per_second": 0.415, | |
| "eval_wer": 48.00813613136876, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 6.911557788944724e-06, | |
| "loss": 0.002, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.886432160804021e-06, | |
| "loss": 0.0019, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 6.861306532663318e-06, | |
| "loss": 0.0028, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 6.8361809045226135e-06, | |
| "loss": 0.0024, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "eval_loss": 0.7199321985244751, | |
| "eval_runtime": 1992.5899, | |
| "eval_samples_per_second": 4.339, | |
| "eval_steps_per_second": 0.434, | |
| "eval_wer": 46.86874700269551, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 6.81105527638191e-06, | |
| "loss": 0.0024, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 6.785929648241206e-06, | |
| "loss": 0.0019, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 6.760804020100503e-06, | |
| "loss": 0.0024, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 6.735678391959799e-06, | |
| "loss": 0.0033, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "eval_loss": 0.7249542474746704, | |
| "eval_runtime": 2175.7785, | |
| "eval_samples_per_second": 3.974, | |
| "eval_steps_per_second": 0.398, | |
| "eval_wer": 48.68945444924013, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 6.710552763819096e-06, | |
| "loss": 0.0021, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 6.685427135678393e-06, | |
| "loss": 0.0014, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 6.660301507537689e-06, | |
| "loss": 0.0011, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 6.6351758793969856e-06, | |
| "loss": 0.0017, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "eval_loss": 0.7241615653038025, | |
| "eval_runtime": 2420.7565, | |
| "eval_samples_per_second": 3.572, | |
| "eval_steps_per_second": 0.357, | |
| "eval_wer": 49.044996775313784, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 6.610050251256281e-06, | |
| "loss": 0.0019, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 6.584924623115578e-06, | |
| "loss": 0.0014, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 6.5597989949748754e-06, | |
| "loss": 0.0011, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 6.534673366834171e-06, | |
| "loss": 0.0016, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "eval_loss": 0.7358579039573669, | |
| "eval_runtime": 2057.6253, | |
| "eval_samples_per_second": 4.202, | |
| "eval_steps_per_second": 0.42, | |
| "eval_wer": 48.70103024590299, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 6.509547738693468e-06, | |
| "loss": 0.002, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 6.484422110552764e-06, | |
| "loss": 0.0015, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 6.459296482412061e-06, | |
| "loss": 0.0024, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 6.434170854271358e-06, | |
| "loss": 0.0022, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "eval_loss": 0.7220202088356018, | |
| "eval_runtime": 2243.6869, | |
| "eval_samples_per_second": 3.853, | |
| "eval_steps_per_second": 0.386, | |
| "eval_wer": 48.1371235798978, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 6.4090452261306535e-06, | |
| "loss": 0.0021, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 6.38391959798995e-06, | |
| "loss": 0.0013, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 6.358793969849246e-06, | |
| "loss": 0.0014, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 6.333668341708543e-06, | |
| "loss": 0.0016, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "eval_loss": 0.7430799007415771, | |
| "eval_runtime": 1822.7961, | |
| "eval_samples_per_second": 4.743, | |
| "eval_steps_per_second": 0.475, | |
| "eval_wer": 46.75629640654198, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 6.30854271356784e-06, | |
| "loss": 0.0008, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 6.283417085427136e-06, | |
| "loss": 0.0014, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 6.258291457286433e-06, | |
| "loss": 0.001, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 6.233165829145729e-06, | |
| "loss": 0.0012, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "eval_loss": 0.7563586235046387, | |
| "eval_runtime": 2100.7282, | |
| "eval_samples_per_second": 4.116, | |
| "eval_steps_per_second": 0.412, | |
| "eval_wer": 47.014271303600076, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "learning_rate": 6.208040201005026e-06, | |
| "loss": 0.0017, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 6.182914572864322e-06, | |
| "loss": 0.0015, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 6.157788944723618e-06, | |
| "loss": 0.0012, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 6.1326633165829155e-06, | |
| "loss": 0.0014, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "eval_loss": 0.7769792079925537, | |
| "eval_runtime": 2049.0992, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.422, | |
| "eval_wer": 47.02419341502539, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 6.107537688442211e-06, | |
| "loss": 0.0011, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 6.082412060301508e-06, | |
| "loss": 0.001, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 6.057286432160805e-06, | |
| "loss": 0.0015, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 6.032160804020101e-06, | |
| "loss": 0.0008, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "eval_loss": 0.8116338849067688, | |
| "eval_runtime": 2088.1418, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 0.414, | |
| "eval_wer": 48.46951431264573, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 6.007035175879398e-06, | |
| "loss": 0.0015, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 5.9819095477386935e-06, | |
| "loss": 0.0008, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 5.95678391959799e-06, | |
| "loss": 0.0016, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 5.9316582914572876e-06, | |
| "loss": 0.0015, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "eval_loss": 0.7622503638267517, | |
| "eval_runtime": 2010.7151, | |
| "eval_samples_per_second": 4.3, | |
| "eval_steps_per_second": 0.43, | |
| "eval_wer": 48.092474078483896, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 5.906532663316583e-06, | |
| "loss": 0.0016, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 5.88140703517588e-06, | |
| "loss": 0.002, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 16.12, | |
| "learning_rate": 5.856281407035176e-06, | |
| "loss": 0.0015, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 16.22, | |
| "learning_rate": 5.831155778894473e-06, | |
| "loss": 0.002, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.22, | |
| "eval_loss": 0.7698885202407837, | |
| "eval_runtime": 1914.0687, | |
| "eval_samples_per_second": 4.517, | |
| "eval_steps_per_second": 0.452, | |
| "eval_wer": 47.72535595574738, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 16.31, | |
| "learning_rate": 5.80603015075377e-06, | |
| "loss": 0.0013, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 5.780904522613066e-06, | |
| "loss": 0.0017, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 5.755778894472362e-06, | |
| "loss": 0.0023, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 5.730653266331658e-06, | |
| "loss": 0.001, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "eval_loss": 0.7630722522735596, | |
| "eval_runtime": 1923.0045, | |
| "eval_samples_per_second": 4.496, | |
| "eval_steps_per_second": 0.45, | |
| "eval_wer": 46.87536174364572, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 5.7055276381909555e-06, | |
| "loss": 0.0022, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 5.680402010050252e-06, | |
| "loss": 0.0012, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 5.655276381909548e-06, | |
| "loss": 0.0018, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 5.6301507537688445e-06, | |
| "loss": 0.0009, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_loss": 0.7591461539268494, | |
| "eval_runtime": 1922.4876, | |
| "eval_samples_per_second": 4.497, | |
| "eval_steps_per_second": 0.45, | |
| "eval_wer": 48.416596385044066, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 5.605025125628141e-06, | |
| "loss": 0.0012, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "learning_rate": 5.579899497487438e-06, | |
| "loss": 0.0009, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 5.554773869346734e-06, | |
| "loss": 0.0006, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 5.52964824120603e-06, | |
| "loss": 0.0008, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "eval_loss": 0.779658317565918, | |
| "eval_runtime": 1935.42, | |
| "eval_samples_per_second": 4.467, | |
| "eval_steps_per_second": 0.447, | |
| "eval_wer": 47.17798614211771, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 5.504522613065328e-06, | |
| "loss": 0.0022, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 5.479396984924623e-06, | |
| "loss": 0.0008, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 5.45427135678392e-06, | |
| "loss": 0.0016, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 5.429145728643217e-06, | |
| "loss": 0.0008, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "eval_loss": 0.7850877046585083, | |
| "eval_runtime": 1838.7142, | |
| "eval_samples_per_second": 4.702, | |
| "eval_steps_per_second": 0.47, | |
| "eval_wer": 46.76621851796729, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 5.404020100502513e-06, | |
| "loss": 0.0011, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 5.37889447236181e-06, | |
| "loss": 0.0007, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 5.353768844221106e-06, | |
| "loss": 0.0015, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "learning_rate": 5.328643216080402e-06, | |
| "loss": 0.0007, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "eval_loss": 0.7897337079048157, | |
| "eval_runtime": 1943.7204, | |
| "eval_samples_per_second": 4.448, | |
| "eval_steps_per_second": 0.445, | |
| "eval_wer": 48.315721585553405, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 5.3035175879397e-06, | |
| "loss": 0.0007, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 5.2783919597989955e-06, | |
| "loss": 0.0006, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 5.253266331658292e-06, | |
| "loss": 0.0007, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 5.228140703517588e-06, | |
| "loss": 0.0006, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "eval_loss": 0.7760252952575684, | |
| "eval_runtime": 1927.3698, | |
| "eval_samples_per_second": 4.486, | |
| "eval_steps_per_second": 0.449, | |
| "eval_wer": 48.806866101106316, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 5.2030150753768845e-06, | |
| "loss": 0.001, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 5.177889447236182e-06, | |
| "loss": 0.0008, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 5.152763819095478e-06, | |
| "loss": 0.0017, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 5.127638190954774e-06, | |
| "loss": 0.0016, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_loss": 0.7762993574142456, | |
| "eval_runtime": 2000.3946, | |
| "eval_samples_per_second": 4.322, | |
| "eval_steps_per_second": 0.432, | |
| "eval_wer": 47.97175505614261, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 5.10251256281407e-06, | |
| "loss": 0.0011, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 5.077386934673368e-06, | |
| "loss": 0.0006, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "learning_rate": 5.052261306532664e-06, | |
| "loss": 0.0006, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 5.02713567839196e-06, | |
| "loss": 0.0009, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "eval_loss": 0.8151038289070129, | |
| "eval_runtime": 1941.3748, | |
| "eval_samples_per_second": 4.454, | |
| "eval_steps_per_second": 0.446, | |
| "eval_wer": 48.158621487985975, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 5.002010050251257e-06, | |
| "loss": 0.0008, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "learning_rate": 4.976884422110553e-06, | |
| "loss": 0.0012, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 4.95175879396985e-06, | |
| "loss": 0.001, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 4.9266331658291465e-06, | |
| "loss": 0.0004, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "eval_loss": 0.7967365384101868, | |
| "eval_runtime": 1771.7869, | |
| "eval_samples_per_second": 4.88, | |
| "eval_steps_per_second": 0.488, | |
| "eval_wer": 47.55668006151709, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 4.901507537688442e-06, | |
| "loss": 0.0007, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "learning_rate": 4.876381909547739e-06, | |
| "loss": 0.0007, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 19.98, | |
| "learning_rate": 4.8512562814070355e-06, | |
| "loss": 0.0009, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 20.08, | |
| "learning_rate": 4.826130653266332e-06, | |
| "loss": 0.0007, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 20.08, | |
| "eval_loss": 0.8094375729560852, | |
| "eval_runtime": 1764.7964, | |
| "eval_samples_per_second": 4.899, | |
| "eval_steps_per_second": 0.49, | |
| "eval_wer": 46.78606274081791, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 20.17, | |
| "learning_rate": 4.801005025125629e-06, | |
| "loss": 0.0007, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 4.7758793969849245e-06, | |
| "loss": 0.0012, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 20.37, | |
| "learning_rate": 4.750753768844221e-06, | |
| "loss": 0.0008, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 20.46, | |
| "learning_rate": 4.725628140703518e-06, | |
| "loss": 0.001, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.46, | |
| "eval_loss": 0.8205662369728088, | |
| "eval_runtime": 1833.049, | |
| "eval_samples_per_second": 4.717, | |
| "eval_steps_per_second": 0.472, | |
| "eval_wer": 47.15648823402954, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "learning_rate": 4.700502512562814e-06, | |
| "loss": 0.0013, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 4.675376884422111e-06, | |
| "loss": 0.0007, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 20.75, | |
| "learning_rate": 4.650251256281408e-06, | |
| "loss": 0.0007, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "learning_rate": 4.625125628140703e-06, | |
| "loss": 0.0008, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "eval_loss": 0.8015366792678833, | |
| "eval_runtime": 1825.3401, | |
| "eval_samples_per_second": 4.737, | |
| "eval_steps_per_second": 0.474, | |
| "eval_wer": 47.621173785781615, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 0.0007, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 21.04, | |
| "learning_rate": 4.574874371859297e-06, | |
| "loss": 0.0006, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 21.14, | |
| "learning_rate": 4.549748743718593e-06, | |
| "loss": 0.0005, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "learning_rate": 4.52462311557789e-06, | |
| "loss": 0.0004, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "eval_loss": 0.8104465007781982, | |
| "eval_runtime": 1735.3093, | |
| "eval_samples_per_second": 4.982, | |
| "eval_steps_per_second": 0.498, | |
| "eval_wer": 47.220981958294054, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 4.499497487437186e-06, | |
| "loss": 0.0004, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 4.474371859296483e-06, | |
| "loss": 0.0005, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 4.44924623115578e-06, | |
| "loss": 0.001, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 21.62, | |
| "learning_rate": 4.4241206030150755e-06, | |
| "loss": 0.0003, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.62, | |
| "eval_loss": 0.8020026683807373, | |
| "eval_runtime": 1798.7419, | |
| "eval_samples_per_second": 4.807, | |
| "eval_steps_per_second": 0.481, | |
| "eval_wer": 48.145392006085565, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 4.398994974874372e-06, | |
| "loss": 0.0008, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 21.81, | |
| "learning_rate": 4.373869346733669e-06, | |
| "loss": 0.0004, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "learning_rate": 4.348743718592965e-06, | |
| "loss": 0.0006, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 4.323618090452262e-06, | |
| "loss": 0.0004, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "eval_loss": 0.8294846415519714, | |
| "eval_runtime": 1827.1151, | |
| "eval_samples_per_second": 4.732, | |
| "eval_steps_per_second": 0.473, | |
| "eval_wer": 46.94150915314779, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 22.1, | |
| "learning_rate": 4.298492462311558e-06, | |
| "loss": 0.0002, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 4.273366834170854e-06, | |
| "loss": 0.0003, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 22.3, | |
| "learning_rate": 4.248241206030151e-06, | |
| "loss": 0.0002, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 4.223115577889448e-06, | |
| "loss": 0.0004, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "eval_loss": 0.822780191898346, | |
| "eval_runtime": 1778.1094, | |
| "eval_samples_per_second": 4.862, | |
| "eval_steps_per_second": 0.486, | |
| "eval_wer": 46.61077210563741, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 22.49, | |
| "learning_rate": 4.197989949748744e-06, | |
| "loss": 0.0003, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 22.59, | |
| "learning_rate": 4.172864321608041e-06, | |
| "loss": 0.0003, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 4.147738693467337e-06, | |
| "loss": 0.0004, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 4.122613065326633e-06, | |
| "loss": 0.0005, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "eval_loss": 0.8386306166648865, | |
| "eval_runtime": 1804.5855, | |
| "eval_samples_per_second": 4.791, | |
| "eval_steps_per_second": 0.479, | |
| "eval_wer": 48.09743513419656, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 4.09748743718593e-06, | |
| "loss": 0.0007, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "learning_rate": 4.0723618090452265e-06, | |
| "loss": 0.0013, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 23.07, | |
| "learning_rate": 4.047236180904523e-06, | |
| "loss": 0.0008, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "learning_rate": 4.02211055276382e-06, | |
| "loss": 0.0007, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "eval_loss": 0.8414955735206604, | |
| "eval_runtime": 1746.5835, | |
| "eval_samples_per_second": 4.95, | |
| "eval_steps_per_second": 0.495, | |
| "eval_wer": 46.61407947611252, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 23.26, | |
| "learning_rate": 3.997989949748744e-06, | |
| "loss": 0.0004, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 3.97286432160804e-06, | |
| "loss": 0.0004, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 23.46, | |
| "learning_rate": 3.947738693467337e-06, | |
| "loss": 0.0006, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "learning_rate": 3.9226130653266335e-06, | |
| "loss": 0.0003, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "eval_loss": 0.8283448815345764, | |
| "eval_runtime": 1775.2653, | |
| "eval_samples_per_second": 4.87, | |
| "eval_steps_per_second": 0.487, | |
| "eval_wer": 46.32633824477848, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 23.65, | |
| "learning_rate": 3.89748743718593e-06, | |
| "loss": 0.0003, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 3.872361809045227e-06, | |
| "loss": 0.0011, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 3.8472361809045225e-06, | |
| "loss": 0.0003, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 23.94, | |
| "learning_rate": 3.822110552763819e-06, | |
| "loss": 0.0005, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 23.94, | |
| "eval_loss": 0.8341825604438782, | |
| "eval_runtime": 1685.2846, | |
| "eval_samples_per_second": 5.13, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 45.965834862992175, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 3.796984924623116e-06, | |
| "loss": 0.0003, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "learning_rate": 3.7718592964824124e-06, | |
| "loss": 0.0008, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 24.23, | |
| "learning_rate": 3.746733668341709e-06, | |
| "loss": 0.0003, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 3.721608040201005e-06, | |
| "loss": 0.0002, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "eval_loss": 0.8378849029541016, | |
| "eval_runtime": 1806.9028, | |
| "eval_samples_per_second": 4.785, | |
| "eval_steps_per_second": 0.479, | |
| "eval_wer": 46.624001587537826, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 3.6964824120603014e-06, | |
| "loss": 0.0002, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 3.6713567839195984e-06, | |
| "loss": 0.0002, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 24.61, | |
| "learning_rate": 3.646231155778895e-06, | |
| "loss": 0.0004, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "learning_rate": 3.6211055276381912e-06, | |
| "loss": 0.0005, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "eval_loss": 0.8371052742004395, | |
| "eval_runtime": 1889.3529, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 0.458, | |
| "eval_wer": 48.080898281821035, | |
| "step": 6400 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 10000, | |
| "num_train_epochs": 39, | |
| "save_steps": 100, | |
| "total_flos": 1.033943772266496e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |