| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.999015425008205, | |
| "global_step": 11415, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.7125e-06, | |
| "loss": 9.2501, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.4625e-06, | |
| "loss": 6.0161, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.1212499999999998e-05, | |
| "loss": 4.0333, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.49625e-05, | |
| "loss": 3.449, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8712499999999997e-05, | |
| "loss": 3.1638, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 3.0685720443725586, | |
| "eval_runtime": 399.7202, | |
| "eval_samples_per_second": 13.372, | |
| "eval_steps_per_second": 0.838, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.2462499999999997e-05, | |
| "loss": 3.0226, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.6212499999999997e-05, | |
| "loss": 2.9748, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.99625e-05, | |
| "loss": 2.9583, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.37125e-05, | |
| "loss": 2.9372, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.7462499999999996e-05, | |
| "loss": 2.9311, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 2.920839309692383, | |
| "eval_runtime": 390.9897, | |
| "eval_samples_per_second": 13.67, | |
| "eval_steps_per_second": 0.857, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.12125e-05, | |
| "loss": 2.9082, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.4962499999999995e-05, | |
| "loss": 2.8906, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.871249999999999e-05, | |
| "loss": 2.8496, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 5.2462499999999994e-05, | |
| "loss": 2.7544, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.62125e-05, | |
| "loss": 2.4175, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.5009071826934814, | |
| "eval_runtime": 386.8095, | |
| "eval_samples_per_second": 13.818, | |
| "eval_steps_per_second": 0.866, | |
| "eval_wer": 0.904880074758592, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 5.9962499999999994e-05, | |
| "loss": 2.07, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 6.37125e-05, | |
| "loss": 1.7743, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.746249999999999e-05, | |
| "loss": 1.6002, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.121249999999999e-05, | |
| "loss": 1.5316, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.49625e-05, | |
| "loss": 1.4442, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.4426315724849701, | |
| "eval_runtime": 388.1138, | |
| "eval_samples_per_second": 13.772, | |
| "eval_steps_per_second": 0.863, | |
| "eval_wer": 0.37832000830651025, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.42113648433351e-05, | |
| "loss": 1.4054, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.341476367498672e-05, | |
| "loss": 1.3519, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.261816250663834e-05, | |
| "loss": 1.3285, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.182156133828995e-05, | |
| "loss": 1.2726, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 7.102496016994158e-05, | |
| "loss": 1.2624, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 0.3192683756351471, | |
| "eval_runtime": 387.478, | |
| "eval_samples_per_second": 13.794, | |
| "eval_steps_per_second": 0.865, | |
| "eval_wer": 0.29977157096874674, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 7.022835900159319e-05, | |
| "loss": 1.2737, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 6.943175783324481e-05, | |
| "loss": 1.2333, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 6.863515666489644e-05, | |
| "loss": 1.2028, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 6.783855549654805e-05, | |
| "loss": 1.1867, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 6.704992033988316e-05, | |
| "loss": 1.1889, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 0.2867003381252289, | |
| "eval_runtime": 384.7872, | |
| "eval_samples_per_second": 13.891, | |
| "eval_steps_per_second": 0.871, | |
| "eval_wer": 0.2630048800747586, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 6.625331917153477e-05, | |
| "loss": 1.1945, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.54567180031864e-05, | |
| "loss": 1.1473, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.466011683483802e-05, | |
| "loss": 1.1408, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 6.386351566648965e-05, | |
| "loss": 1.1376, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 6.306691449814126e-05, | |
| "loss": 1.1315, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 0.25655683875083923, | |
| "eval_runtime": 384.1782, | |
| "eval_samples_per_second": 13.913, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.2443775308898349, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 6.227031332979288e-05, | |
| "loss": 1.1225, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 6.14737121614445e-05, | |
| "loss": 1.1386, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 6.067711099309612e-05, | |
| "loss": 1.1098, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 5.9880509824747736e-05, | |
| "loss": 1.1149, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 5.908390865639936e-05, | |
| "loss": 1.0864, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "eval_loss": 0.23677974939346313, | |
| "eval_runtime": 394.8394, | |
| "eval_samples_per_second": 13.537, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.2293946630671789, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 5.828730748805098e-05, | |
| "loss": 1.0996, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 5.74907063197026e-05, | |
| "loss": 1.0714, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 5.6694105151354214e-05, | |
| "loss": 1.0849, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 5.589750398300583e-05, | |
| "loss": 1.069, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 5.5100902814657456e-05, | |
| "loss": 1.093, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_loss": 0.2239702194929123, | |
| "eval_runtime": 385.949, | |
| "eval_samples_per_second": 13.849, | |
| "eval_steps_per_second": 0.868, | |
| "eval_wer": 0.21509708233828262, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 5.4304301646309074e-05, | |
| "loss": 1.0677, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 5.35077004779607e-05, | |
| "loss": 1.089, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 5.2711099309612316e-05, | |
| "loss": 1.0475, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 5.191449814126394e-05, | |
| "loss": 1.0455, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 5.111789697291556e-05, | |
| "loss": 1.0368, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "eval_loss": 0.21173720061779022, | |
| "eval_runtime": 384.8447, | |
| "eval_samples_per_second": 13.889, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.205575744990136, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 5.032129580456717e-05, | |
| "loss": 1.0459, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 4.9524694636218794e-05, | |
| "loss": 1.0375, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 4.872809346787041e-05, | |
| "loss": 1.033, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 4.7931492299522036e-05, | |
| "loss": 1.0291, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 4.7134891131173654e-05, | |
| "loss": 1.0178, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "eval_loss": 0.20199091732501984, | |
| "eval_runtime": 385.2062, | |
| "eval_samples_per_second": 13.876, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.19541065309936662, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.634625597450876e-05, | |
| "loss": 1.0258, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 4.554965480616038e-05, | |
| "loss": 1.0161, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 4.4753053637812e-05, | |
| "loss": 1.0443, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 4.395645246946362e-05, | |
| "loss": 1.0143, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 4.3159851301115245e-05, | |
| "loss": 1.0035, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "eval_loss": 0.20046772062778473, | |
| "eval_runtime": 386.8691, | |
| "eval_samples_per_second": 13.816, | |
| "eval_steps_per_second": 0.866, | |
| "eval_wer": 0.192378776866369, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.2363250132766856e-05, | |
| "loss": 1.0233, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 4.1566648964418474e-05, | |
| "loss": 0.9893, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 4.07700477960701e-05, | |
| "loss": 0.9896, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 3.9973446627721716e-05, | |
| "loss": 0.9879, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 3.917684545937334e-05, | |
| "loss": 0.9759, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "eval_loss": 0.1971476823091507, | |
| "eval_runtime": 383.9373, | |
| "eval_samples_per_second": 13.922, | |
| "eval_steps_per_second": 0.873, | |
| "eval_wer": 0.18630464126258955, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 3.838024429102496e-05, | |
| "loss": 0.9969, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.758364312267658e-05, | |
| "loss": 1.0003, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 3.6787041954328194e-05, | |
| "loss": 1.0125, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 3.599044078597982e-05, | |
| "loss": 0.9907, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.5193839617631436e-05, | |
| "loss": 0.9795, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 0.18917934596538544, | |
| "eval_runtime": 385.8026, | |
| "eval_samples_per_second": 13.854, | |
| "eval_steps_per_second": 0.868, | |
| "eval_wer": 0.18121690374831273, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 3.4397238449283054e-05, | |
| "loss": 0.9768, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 3.360063728093468e-05, | |
| "loss": 1.0074, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 3.2804036112586296e-05, | |
| "loss": 0.9729, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 3.2007434944237914e-05, | |
| "loss": 0.9584, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 3.121083377588953e-05, | |
| "loss": 0.9601, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "eval_loss": 0.18627513945102692, | |
| "eval_runtime": 384.7444, | |
| "eval_samples_per_second": 13.892, | |
| "eval_steps_per_second": 0.871, | |
| "eval_wer": 0.17949330287612916, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 3.0414232607541153e-05, | |
| "loss": 0.9729, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 2.9617631439192774e-05, | |
| "loss": 0.9712, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 2.882899628252788e-05, | |
| "loss": 0.9746, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 2.80323951141795e-05, | |
| "loss": 0.9595, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 2.7235793945831116e-05, | |
| "loss": 0.9673, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "eval_loss": 0.1808742731809616, | |
| "eval_runtime": 383.472, | |
| "eval_samples_per_second": 13.938, | |
| "eval_steps_per_second": 0.874, | |
| "eval_wer": 0.17611878309625167, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 2.6439192777482737e-05, | |
| "loss": 0.9465, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 2.564259160913436e-05, | |
| "loss": 0.9628, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 2.484599044078598e-05, | |
| "loss": 0.946, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.4049389272437594e-05, | |
| "loss": 0.9316, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 2.3252788104089215e-05, | |
| "loss": 0.9233, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "eval_loss": 0.18183015286922455, | |
| "eval_runtime": 379.914, | |
| "eval_samples_per_second": 14.069, | |
| "eval_steps_per_second": 0.882, | |
| "eval_wer": 0.17553732738033434, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 2.2456186935740836e-05, | |
| "loss": 0.9521, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 2.1659585767392457e-05, | |
| "loss": 0.9411, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 2.0862984599044075e-05, | |
| "loss": 0.9333, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 2.0066383430695696e-05, | |
| "loss": 0.937, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 1.9269782262347317e-05, | |
| "loss": 0.9382, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "eval_loss": 0.17674756050109863, | |
| "eval_runtime": 384.6492, | |
| "eval_samples_per_second": 13.896, | |
| "eval_steps_per_second": 0.871, | |
| "eval_wer": 0.1741459869172464, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 1.847318109399894e-05, | |
| "loss": 0.9453, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 1.7676579925650556e-05, | |
| "loss": 0.9626, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 1.6879978757302177e-05, | |
| "loss": 0.9289, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 1.6083377588953795e-05, | |
| "loss": 0.9282, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 1.5286776420605416e-05, | |
| "loss": 0.9242, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "eval_loss": 0.17428240180015564, | |
| "eval_runtime": 381.3036, | |
| "eval_samples_per_second": 14.018, | |
| "eval_steps_per_second": 0.879, | |
| "eval_wer": 0.17025231024815698, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 1.4490175252257036e-05, | |
| "loss": 0.9273, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 1.3693574083908655e-05, | |
| "loss": 0.9254, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 1.2896972915560275e-05, | |
| "loss": 0.9209, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.2100371747211896e-05, | |
| "loss": 0.9292, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 1.1303770578863514e-05, | |
| "loss": 0.9703, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "eval_loss": 0.17106124758720398, | |
| "eval_runtime": 382.5906, | |
| "eval_samples_per_second": 13.971, | |
| "eval_steps_per_second": 0.876, | |
| "eval_wer": 0.17105181185754334, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 1.0507169410515135e-05, | |
| "loss": 0.9186, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 9.710568242166754e-06, | |
| "loss": 0.9227, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 8.913967073818375e-06, | |
| "loss": 0.909, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 8.117365905469995e-06, | |
| "loss": 0.9028, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 7.328730748805097e-06, | |
| "loss": 0.9139, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "eval_loss": 0.1718469262123108, | |
| "eval_runtime": 380.6631, | |
| "eval_samples_per_second": 14.041, | |
| "eval_steps_per_second": 0.88, | |
| "eval_wer": 0.1671996677395909, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 6.532129580456718e-06, | |
| "loss": 0.9146, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 5.735528412108338e-06, | |
| "loss": 0.9239, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 4.938927243759957e-06, | |
| "loss": 0.9351, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 4.142326075411577e-06, | |
| "loss": 0.9127, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "learning_rate": 3.3457249070631965e-06, | |
| "loss": 0.9073, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "eval_loss": 0.16996563971042633, | |
| "eval_runtime": 380.1012, | |
| "eval_samples_per_second": 14.062, | |
| "eval_steps_per_second": 0.881, | |
| "eval_wer": 0.1664728480946942, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 2.5491237387148164e-06, | |
| "loss": 0.9023, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 1.76048858204992e-06, | |
| "loss": 0.908, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 9.6388741370154e-07, | |
| "loss": 0.9096, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 1.6728624535315985e-07, | |
| "loss": 0.9436, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 11415, | |
| "total_flos": 1.4956070851005566e+20, | |
| "train_loss": 1.3962327468410898, | |
| "train_runtime": 63316.5045, | |
| "train_samples_per_second": 11.549, | |
| "train_steps_per_second": 0.18 | |
| } | |
| ], | |
| "max_steps": 11415, | |
| "num_train_epochs": 15, | |
| "total_flos": 1.4956070851005566e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |