| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 9650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3.2333333333333334e-06, | |
| "loss": 11.6585, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 6.566666666666667e-06, | |
| "loss": 3.4349, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.900000000000002e-06, | |
| "loss": 3.0733, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.3233333333333334e-05, | |
| "loss": 2.0674, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 1.341134786605835, | |
| "eval_runtime": 163.433, | |
| "eval_samples_per_second": 16.478, | |
| "eval_steps_per_second": 1.034, | |
| "eval_wer": 0.8834933444645424, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.6566666666666665e-05, | |
| "loss": 1.6791, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.9900000000000003e-05, | |
| "loss": 1.5037, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 2.3233333333333333e-05, | |
| "loss": 1.3966, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.6566666666666668e-05, | |
| "loss": 1.324, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 0.9311084747314453, | |
| "eval_runtime": 162.7031, | |
| "eval_samples_per_second": 16.552, | |
| "eval_steps_per_second": 1.039, | |
| "eval_wer": 0.7142062056490887, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.9900000000000002e-05, | |
| "loss": 1.2854, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 3.323333333333333e-05, | |
| "loss": 1.237, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 3.656666666666666e-05, | |
| "loss": 1.2105, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 3.99e-05, | |
| "loss": 1.2023, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_loss": 0.8060462474822998, | |
| "eval_runtime": 163.1532, | |
| "eval_samples_per_second": 16.506, | |
| "eval_steps_per_second": 1.036, | |
| "eval_wer": 0.6170400259728213, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 4.323333333333334e-05, | |
| "loss": 1.1816, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 4.656666666666667e-05, | |
| "loss": 1.1895, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 4.99e-05, | |
| "loss": 1.1743, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 4.940490797546012e-05, | |
| "loss": 1.1573, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "eval_loss": 0.741489589214325, | |
| "eval_runtime": 162.3319, | |
| "eval_samples_per_second": 16.589, | |
| "eval_steps_per_second": 1.041, | |
| "eval_wer": 0.49724038773711793, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 4.879141104294479e-05, | |
| "loss": 1.1409, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 4.817791411042945e-05, | |
| "loss": 1.1314, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 4.756441717791411e-05, | |
| "loss": 1.1364, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 4.695092024539878e-05, | |
| "loss": 1.1117, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "eval_loss": 0.7248229384422302, | |
| "eval_runtime": 162.1078, | |
| "eval_samples_per_second": 16.612, | |
| "eval_steps_per_second": 1.043, | |
| "eval_wer": 0.4587913362088957, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 4.633742331288344e-05, | |
| "loss": 1.1017, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.5723926380368096e-05, | |
| "loss": 1.0979, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 4.511042944785277e-05, | |
| "loss": 1.0932, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 4.4496932515337425e-05, | |
| "loss": 1.0672, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "eval_loss": 0.6728883981704712, | |
| "eval_runtime": 161.2322, | |
| "eval_samples_per_second": 16.703, | |
| "eval_steps_per_second": 1.048, | |
| "eval_wer": 0.4349983766986689, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 4.388343558282208e-05, | |
| "loss": 1.0797, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 4.3269938650306755e-05, | |
| "loss": 1.0521, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 4.265644171779141e-05, | |
| "loss": 1.051, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 4.204294478527608e-05, | |
| "loss": 1.0336, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "eval_loss": 0.7116607427597046, | |
| "eval_runtime": 160.91, | |
| "eval_samples_per_second": 16.736, | |
| "eval_steps_per_second": 1.05, | |
| "eval_wer": 0.4345809563563842, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 4.142944785276074e-05, | |
| "loss": 1.0411, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 4.08159509202454e-05, | |
| "loss": 1.0135, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 16.06, | |
| "learning_rate": 4.0202453987730065e-05, | |
| "loss": 1.0102, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 3.958895705521473e-05, | |
| "loss": 1.0025, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "eval_loss": 0.7018883228302002, | |
| "eval_runtime": 160.9879, | |
| "eval_samples_per_second": 16.728, | |
| "eval_steps_per_second": 1.05, | |
| "eval_wer": 0.4271601502713232, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 3.897546012269939e-05, | |
| "loss": 0.9754, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 17.62, | |
| "learning_rate": 3.836196319018405e-05, | |
| "loss": 0.9695, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 3.774846625766871e-05, | |
| "loss": 0.9663, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 18.65, | |
| "learning_rate": 3.7134969325153375e-05, | |
| "loss": 0.9578, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 18.65, | |
| "eval_loss": 0.6791622042655945, | |
| "eval_runtime": 162.2664, | |
| "eval_samples_per_second": 16.596, | |
| "eval_steps_per_second": 1.041, | |
| "eval_wer": 0.41176197764482164, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 3.652147239263804e-05, | |
| "loss": 0.9392, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 3.59079754601227e-05, | |
| "loss": 0.9504, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 3.529447852760737e-05, | |
| "loss": 0.9389, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 3.468098159509203e-05, | |
| "loss": 0.9272, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "eval_loss": 0.6863027811050415, | |
| "eval_runtime": 161.4481, | |
| "eval_samples_per_second": 16.68, | |
| "eval_steps_per_second": 1.047, | |
| "eval_wer": 0.41561152080144703, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "learning_rate": 3.4067484662576685e-05, | |
| "loss": 0.926, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 3.3453987730061356e-05, | |
| "loss": 0.9145, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 3.284662576687117e-05, | |
| "loss": 0.9118, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "learning_rate": 3.223312883435583e-05, | |
| "loss": 0.9321, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "eval_loss": 0.6534942984580994, | |
| "eval_runtime": 160.5933, | |
| "eval_samples_per_second": 16.769, | |
| "eval_steps_per_second": 1.052, | |
| "eval_wer": 0.3971986457028895, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 23.32, | |
| "learning_rate": 3.161963190184049e-05, | |
| "loss": 0.9064, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 3.100613496932516e-05, | |
| "loss": 0.8915, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 24.35, | |
| "learning_rate": 3.0392638036809817e-05, | |
| "loss": 0.8907, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "learning_rate": 2.977914110429448e-05, | |
| "loss": 0.8802, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "eval_loss": 0.6766195297241211, | |
| "eval_runtime": 161.8159, | |
| "eval_samples_per_second": 16.642, | |
| "eval_steps_per_second": 1.044, | |
| "eval_wer": 0.39056630026436623, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 25.39, | |
| "learning_rate": 2.9171779141104295e-05, | |
| "loss": 0.8834, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "learning_rate": 2.855828220858896e-05, | |
| "loss": 0.866, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 26.42, | |
| "learning_rate": 2.794478527607362e-05, | |
| "loss": 0.8497, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 2.7331288343558282e-05, | |
| "loss": 0.844, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "eval_loss": 0.678193986415863, | |
| "eval_runtime": 161.4084, | |
| "eval_samples_per_second": 16.684, | |
| "eval_steps_per_second": 1.047, | |
| "eval_wer": 0.39492602383933956, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 27.46, | |
| "learning_rate": 2.6717791411042947e-05, | |
| "loss": 0.8466, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 27.98, | |
| "learning_rate": 2.6104294478527608e-05, | |
| "loss": 0.831, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "learning_rate": 2.5490797546012273e-05, | |
| "loss": 0.82, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.4877300613496934e-05, | |
| "loss": 0.8387, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_loss": 0.6915661692619324, | |
| "eval_runtime": 161.098, | |
| "eval_samples_per_second": 16.717, | |
| "eval_steps_per_second": 1.049, | |
| "eval_wer": 0.3921432215574417, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 29.53, | |
| "learning_rate": 2.4263803680981595e-05, | |
| "loss": 0.8205, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 30.05, | |
| "learning_rate": 2.3650306748466257e-05, | |
| "loss": 0.8139, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 30.57, | |
| "learning_rate": 2.303680981595092e-05, | |
| "loss": 0.8197, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 31.09, | |
| "learning_rate": 2.2423312883435586e-05, | |
| "loss": 0.8042, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 31.09, | |
| "eval_loss": 0.6805949807167053, | |
| "eval_runtime": 161.7661, | |
| "eval_samples_per_second": 16.647, | |
| "eval_steps_per_second": 1.045, | |
| "eval_wer": 0.3796669913269329, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 31.61, | |
| "learning_rate": 2.1809815950920244e-05, | |
| "loss": 0.7911, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 32.12, | |
| "learning_rate": 2.119631901840491e-05, | |
| "loss": 0.7926, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 2.0582822085889574e-05, | |
| "loss": 0.7922, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 1.9969325153374235e-05, | |
| "loss": 0.793, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "eval_loss": 0.7119700908660889, | |
| "eval_runtime": 161.5775, | |
| "eval_samples_per_second": 16.667, | |
| "eval_steps_per_second": 1.046, | |
| "eval_wer": 0.383052734103242, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 33.68, | |
| "learning_rate": 1.9355828220858896e-05, | |
| "loss": 0.7779, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 34.2, | |
| "learning_rate": 1.874233128834356e-05, | |
| "loss": 0.7739, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 34.72, | |
| "learning_rate": 1.8128834355828222e-05, | |
| "loss": 0.7579, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 35.23, | |
| "learning_rate": 1.7515337423312884e-05, | |
| "loss": 0.7567, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 35.23, | |
| "eval_loss": 0.686227560043335, | |
| "eval_runtime": 161.2767, | |
| "eval_samples_per_second": 16.698, | |
| "eval_steps_per_second": 1.048, | |
| "eval_wer": 0.3808264922777237, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 35.75, | |
| "learning_rate": 1.6901840490797545e-05, | |
| "loss": 0.7623, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 36.27, | |
| "learning_rate": 1.628834355828221e-05, | |
| "loss": 0.7603, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 36.79, | |
| "learning_rate": 1.5674846625766874e-05, | |
| "loss": 0.7416, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 37.31, | |
| "learning_rate": 1.5061349693251534e-05, | |
| "loss": 0.7463, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 37.31, | |
| "eval_loss": 0.6893351078033447, | |
| "eval_runtime": 161.5435, | |
| "eval_samples_per_second": 16.67, | |
| "eval_steps_per_second": 1.046, | |
| "eval_wer": 0.3709011641389546, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 37.82, | |
| "learning_rate": 1.445398773006135e-05, | |
| "loss": 0.7333, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 38.34, | |
| "learning_rate": 1.3840490797546013e-05, | |
| "loss": 0.7142, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 38.86, | |
| "learning_rate": 1.3226993865030676e-05, | |
| "loss": 0.7291, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 39.38, | |
| "learning_rate": 1.2613496932515337e-05, | |
| "loss": 0.7053, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 39.38, | |
| "eval_loss": 0.7095528841018677, | |
| "eval_runtime": 160.1545, | |
| "eval_samples_per_second": 16.815, | |
| "eval_steps_per_second": 1.055, | |
| "eval_wer": 0.3700663234543852, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 39.9, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.727, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 40.41, | |
| "learning_rate": 1.1386503067484663e-05, | |
| "loss": 0.7157, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 40.93, | |
| "learning_rate": 1.0773006134969325e-05, | |
| "loss": 0.6954, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 41.45, | |
| "learning_rate": 1.015950920245399e-05, | |
| "loss": 0.6906, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 41.45, | |
| "eval_loss": 0.6921066045761108, | |
| "eval_runtime": 161.634, | |
| "eval_samples_per_second": 16.661, | |
| "eval_steps_per_second": 1.046, | |
| "eval_wer": 0.3675618014006771, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 41.97, | |
| "learning_rate": 9.54601226993865e-06, | |
| "loss": 0.6817, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 42.49, | |
| "learning_rate": 8.932515337423314e-06, | |
| "loss": 0.6861, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 8.319018404907975e-06, | |
| "loss": 0.6942, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 43.52, | |
| "learning_rate": 7.705521472392638e-06, | |
| "loss": 0.6891, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 43.52, | |
| "eval_loss": 0.7166885733604431, | |
| "eval_runtime": 160.1699, | |
| "eval_samples_per_second": 16.813, | |
| "eval_steps_per_second": 1.055, | |
| "eval_wer": 0.3662631603357915, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 44.04, | |
| "learning_rate": 7.092024539877301e-06, | |
| "loss": 0.6844, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 44.56, | |
| "learning_rate": 6.478527607361963e-06, | |
| "loss": 0.6693, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 45.08, | |
| "learning_rate": 5.865030674846626e-06, | |
| "loss": 0.6703, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "learning_rate": 5.251533742331288e-06, | |
| "loss": 0.658, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "eval_loss": 0.6833298802375793, | |
| "eval_runtime": 159.9929, | |
| "eval_samples_per_second": 16.832, | |
| "eval_steps_per_second": 1.056, | |
| "eval_wer": 0.3580075135661611, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 4.6380368098159506e-06, | |
| "loss": 0.6549, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 46.63, | |
| "learning_rate": 4.0245398773006136e-06, | |
| "loss": 0.6665, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 47.15, | |
| "learning_rate": 3.411042944785276e-06, | |
| "loss": 0.6537, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 47.67, | |
| "learning_rate": 2.7975460122699388e-06, | |
| "loss": 0.6576, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 47.67, | |
| "eval_loss": 0.6914297342300415, | |
| "eval_runtime": 160.7459, | |
| "eval_samples_per_second": 16.753, | |
| "eval_steps_per_second": 1.051, | |
| "eval_wer": 0.3569407726914336, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 2.1840490797546013e-06, | |
| "loss": 0.6601, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 48.7, | |
| "learning_rate": 1.570552147239264e-06, | |
| "loss": 0.6327, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 49.22, | |
| "learning_rate": 9.570552147239263e-07, | |
| "loss": 0.6448, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 49.74, | |
| "learning_rate": 3.43558282208589e-07, | |
| "loss": 0.6358, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 49.74, | |
| "eval_loss": 0.6921652555465698, | |
| "eval_runtime": 161.3961, | |
| "eval_samples_per_second": 16.686, | |
| "eval_steps_per_second": 1.047, | |
| "eval_wer": 0.3551319512082, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 9650, | |
| "total_flos": 1.2240549585337914e+20, | |
| "train_loss": 1.0753348940518237, | |
| "train_runtime": 32646.4121, | |
| "train_samples_per_second": 9.459, | |
| "train_steps_per_second": 0.296 | |
| } | |
| ], | |
| "max_steps": 9650, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.2240549585337914e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |