| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 14200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.789999999999999e-06, | |
| "loss": 13.5868, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.379e-05, | |
| "loss": 5.6931, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.0789999999999996e-05, | |
| "loss": 4.1485, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.779e-05, | |
| "loss": 3.5861, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.479e-05, | |
| "loss": 3.2885, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.178999999999999e-05, | |
| "loss": 3.2023, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 4.878999999999999e-05, | |
| "loss": 3.1447, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 5.579e-05, | |
| "loss": 3.0982, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 6.279e-05, | |
| "loss": 2.9573, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 6.979e-05, | |
| "loss": 2.3964, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 1.225058913230896, | |
| "eval_runtime": 113.8433, | |
| "eval_samples_per_second": 30.103, | |
| "eval_steps_per_second": 0.949, | |
| "eval_wer": 0.878148627762229, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.948560606060606e-05, | |
| "loss": 1.9563, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 6.895530303030303e-05, | |
| "loss": 1.7124, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 6.8425e-05, | |
| "loss": 1.5888, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 6.789469696969696e-05, | |
| "loss": 1.514, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 6.736439393939394e-05, | |
| "loss": 1.4347, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 6.68340909090909e-05, | |
| "loss": 1.4113, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 6.630378787878786e-05, | |
| "loss": 1.4, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 6.577348484848484e-05, | |
| "loss": 1.3486, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 6.52431818181818e-05, | |
| "loss": 1.3427, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 6.471287878787878e-05, | |
| "loss": 1.3176, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 0.3872202932834625, | |
| "eval_runtime": 113.3065, | |
| "eval_samples_per_second": 30.245, | |
| "eval_steps_per_second": 0.953, | |
| "eval_wer": 0.4461756965620953, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 6.418257575757575e-05, | |
| "loss": 1.2983, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 6.365227272727272e-05, | |
| "loss": 1.2845, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 6.312196969696969e-05, | |
| "loss": 1.2803, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 6.259166666666667e-05, | |
| "loss": 1.2482, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.206136363636363e-05, | |
| "loss": 1.2734, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 6.153106060606061e-05, | |
| "loss": 1.2382, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 6.100075757575757e-05, | |
| "loss": 1.2278, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 6.047045454545454e-05, | |
| "loss": 1.2254, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 5.994015151515151e-05, | |
| "loss": 1.2084, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 5.940984848484848e-05, | |
| "loss": 1.1999, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "eval_loss": 0.32438814640045166, | |
| "eval_runtime": 116.219, | |
| "eval_samples_per_second": 29.487, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.39216341534734117, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 5.887954545454545e-05, | |
| "loss": 1.2041, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 5.8349242424242423e-05, | |
| "loss": 1.1884, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 5.781893939393939e-05, | |
| "loss": 1.1938, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 5.728863636363636e-05, | |
| "loss": 1.1871, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 5.675833333333333e-05, | |
| "loss": 1.1859, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 5.62280303030303e-05, | |
| "loss": 1.1824, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.569772727272727e-05, | |
| "loss": 1.1627, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 5.516742424242423e-05, | |
| "loss": 1.1557, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 5.4637121212121204e-05, | |
| "loss": 1.1679, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.4106818181818174e-05, | |
| "loss": 1.1633, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "eval_loss": 0.3014352321624756, | |
| "eval_runtime": 112.4096, | |
| "eval_samples_per_second": 30.487, | |
| "eval_steps_per_second": 0.961, | |
| "eval_wer": 0.3703997660720999, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 5.3576515151515145e-05, | |
| "loss": 1.1435, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 5.3046212121212116e-05, | |
| "loss": 1.14, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 5.252121212121211e-05, | |
| "loss": 1.1508, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 5.199090909090908e-05, | |
| "loss": 1.1158, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 5.146060606060605e-05, | |
| "loss": 1.1181, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 5.093030303030302e-05, | |
| "loss": 1.1156, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 5.039999999999999e-05, | |
| "loss": 1.1205, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 4.986969696969696e-05, | |
| "loss": 1.1364, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 4.933939393939393e-05, | |
| "loss": 1.1098, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 4.8809090909090903e-05, | |
| "loss": 1.1132, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "eval_loss": 0.2912500500679016, | |
| "eval_runtime": 113.7465, | |
| "eval_samples_per_second": 30.128, | |
| "eval_steps_per_second": 0.949, | |
| "eval_wer": 0.3622540624086219, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 4.8278787878787874e-05, | |
| "loss": 1.1102, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 4.7748484848484845e-05, | |
| "loss": 1.12, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 4.7218181818181815e-05, | |
| "loss": 1.1068, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 4.6687878787878786e-05, | |
| "loss": 1.1125, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 19.37, | |
| "learning_rate": 4.6157575757575756e-05, | |
| "loss": 1.0941, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 4.562727272727273e-05, | |
| "loss": 1.0938, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 20.07, | |
| "learning_rate": 4.50969696969697e-05, | |
| "loss": 1.071, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 4.456666666666667e-05, | |
| "loss": 1.0878, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "learning_rate": 4.403636363636364e-05, | |
| "loss": 1.0815, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 21.13, | |
| "learning_rate": 4.3506060606060596e-05, | |
| "loss": 1.0888, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 21.13, | |
| "eval_loss": 0.28635460138320923, | |
| "eval_runtime": 111.8452, | |
| "eval_samples_per_second": 30.641, | |
| "eval_steps_per_second": 0.966, | |
| "eval_wer": 0.3498057562972555, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 21.48, | |
| "learning_rate": 4.2975757575757566e-05, | |
| "loss": 1.0875, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 21.83, | |
| "learning_rate": 4.244545454545454e-05, | |
| "loss": 1.0609, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 4.191515151515151e-05, | |
| "loss": 1.0796, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 4.1390151515151515e-05, | |
| "loss": 1.0701, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 4.0859848484848485e-05, | |
| "loss": 1.0633, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 23.24, | |
| "learning_rate": 4.0329545454545456e-05, | |
| "loss": 1.0491, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 23.59, | |
| "learning_rate": 3.9799242424242427e-05, | |
| "loss": 1.0673, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 23.94, | |
| "learning_rate": 3.927424242424242e-05, | |
| "loss": 1.0574, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 3.874393939393939e-05, | |
| "loss": 1.0371, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 3.821363636363636e-05, | |
| "loss": 1.0487, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "eval_loss": 0.28213828802108765, | |
| "eval_runtime": 109.6819, | |
| "eval_samples_per_second": 31.245, | |
| "eval_steps_per_second": 0.985, | |
| "eval_wer": 0.3434562847236727, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.768333333333333e-05, | |
| "loss": 1.0749, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 25.35, | |
| "learning_rate": 3.71530303030303e-05, | |
| "loss": 1.0492, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 25.7, | |
| "learning_rate": 3.662272727272727e-05, | |
| "loss": 1.0189, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 26.06, | |
| "learning_rate": 3.609242424242424e-05, | |
| "loss": 1.0428, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 26.41, | |
| "learning_rate": 3.556212121212121e-05, | |
| "loss": 1.0372, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 3.503181818181818e-05, | |
| "loss": 1.0324, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 3.450151515151515e-05, | |
| "loss": 1.0244, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 27.46, | |
| "learning_rate": 3.397121212121212e-05, | |
| "loss": 1.0217, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 3.344090909090909e-05, | |
| "loss": 1.024, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "learning_rate": 3.291060606060606e-05, | |
| "loss": 1.0431, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "eval_loss": 0.2738790810108185, | |
| "eval_runtime": 112.4344, | |
| "eval_samples_per_second": 30.48, | |
| "eval_steps_per_second": 0.961, | |
| "eval_wer": 0.33075734157650694, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 3.238030303030303e-05, | |
| "loss": 1.0062, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 28.87, | |
| "learning_rate": 3.185e-05, | |
| "loss": 1.0167, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.1319696969696965e-05, | |
| "loss": 1.0051, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 3.0789393939393936e-05, | |
| "loss": 1.015, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 29.93, | |
| "learning_rate": 3.0259090909090907e-05, | |
| "loss": 1.0221, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 2.9728787878787874e-05, | |
| "loss": 0.9987, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 30.63, | |
| "learning_rate": 2.9198484848484844e-05, | |
| "loss": 1.0008, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 2.8668181818181815e-05, | |
| "loss": 0.9992, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 31.34, | |
| "learning_rate": 2.8143181818181816e-05, | |
| "loss": 1.0122, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 31.69, | |
| "learning_rate": 2.7612878787878786e-05, | |
| "loss": 0.9896, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 31.69, | |
| "eval_loss": 0.2629273533821106, | |
| "eval_runtime": 110.3673, | |
| "eval_samples_per_second": 31.051, | |
| "eval_steps_per_second": 0.979, | |
| "eval_wer": 0.32432432432432434, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 32.04, | |
| "learning_rate": 2.7082575757575757e-05, | |
| "loss": 0.9994, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 32.39, | |
| "learning_rate": 2.6552272727272727e-05, | |
| "loss": 0.9966, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 32.75, | |
| "learning_rate": 2.6021969696969695e-05, | |
| "loss": 0.9905, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 33.1, | |
| "learning_rate": 2.5491666666666665e-05, | |
| "loss": 0.9819, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 33.45, | |
| "learning_rate": 2.4966666666666666e-05, | |
| "loss": 1.0018, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "learning_rate": 2.4436363636363636e-05, | |
| "loss": 0.9881, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 34.15, | |
| "learning_rate": 2.3906060606060604e-05, | |
| "loss": 0.9939, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 34.51, | |
| "learning_rate": 2.3375757575757574e-05, | |
| "loss": 0.9874, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 2.284545454545454e-05, | |
| "loss": 0.9617, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 35.21, | |
| "learning_rate": 2.2315151515151512e-05, | |
| "loss": 0.9839, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 35.21, | |
| "eval_loss": 0.28058063983917236, | |
| "eval_runtime": 111.4323, | |
| "eval_samples_per_second": 30.754, | |
| "eval_steps_per_second": 0.969, | |
| "eval_wer": 0.33079911441580684, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 2.1784848484848483e-05, | |
| "loss": 0.9761, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 35.92, | |
| "learning_rate": 2.1254545454545453e-05, | |
| "loss": 0.9892, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 36.27, | |
| "learning_rate": 2.0724242424242424e-05, | |
| "loss": 0.9712, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 36.62, | |
| "learning_rate": 2.0193939393939394e-05, | |
| "loss": 0.9725, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 36.97, | |
| "learning_rate": 1.966363636363636e-05, | |
| "loss": 0.9738, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "learning_rate": 1.9133333333333332e-05, | |
| "loss": 0.9622, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 37.68, | |
| "learning_rate": 1.86030303030303e-05, | |
| "loss": 0.9612, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "learning_rate": 1.807272727272727e-05, | |
| "loss": 0.9645, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "learning_rate": 1.754242424242424e-05, | |
| "loss": 0.9703, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 38.73, | |
| "learning_rate": 1.701212121212121e-05, | |
| "loss": 0.9586, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 38.73, | |
| "eval_loss": 0.26495224237442017, | |
| "eval_runtime": 115.232, | |
| "eval_samples_per_second": 29.74, | |
| "eval_steps_per_second": 0.937, | |
| "eval_wer": 0.32353064037762647, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 39.08, | |
| "learning_rate": 1.6481818181818178e-05, | |
| "loss": 0.9597, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 1.595151515151515e-05, | |
| "loss": 0.9617, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 39.79, | |
| "learning_rate": 1.542121212121212e-05, | |
| "loss": 0.9615, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 1.489090909090909e-05, | |
| "loss": 0.9476, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 40.49, | |
| "learning_rate": 1.4360606060606059e-05, | |
| "loss": 0.958, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "learning_rate": 1.3830303030303029e-05, | |
| "loss": 0.9515, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 41.2, | |
| "learning_rate": 1.33e-05, | |
| "loss": 0.9525, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 41.55, | |
| "learning_rate": 1.2769696969696969e-05, | |
| "loss": 0.9484, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 41.9, | |
| "learning_rate": 1.2239393939393937e-05, | |
| "loss": 0.9326, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 42.25, | |
| "learning_rate": 1.1719696969696968e-05, | |
| "loss": 0.9501, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 42.25, | |
| "eval_loss": 0.25854310393333435, | |
| "eval_runtime": 111.5579, | |
| "eval_samples_per_second": 30.719, | |
| "eval_steps_per_second": 0.968, | |
| "eval_wer": 0.3173064873219433, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 42.61, | |
| "learning_rate": 1.1189393939393939e-05, | |
| "loss": 0.9395, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 42.96, | |
| "learning_rate": 1.065909090909091e-05, | |
| "loss": 0.9519, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 43.31, | |
| "learning_rate": 1.0128787878787877e-05, | |
| "loss": 0.9445, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 43.66, | |
| "learning_rate": 9.598484848484847e-06, | |
| "loss": 0.9293, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 9.068181818181818e-06, | |
| "loss": 0.9421, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 44.37, | |
| "learning_rate": 8.537878787878787e-06, | |
| "loss": 0.9305, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 8.007575757575757e-06, | |
| "loss": 0.9305, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 45.07, | |
| "learning_rate": 7.477272727272726e-06, | |
| "loss": 0.9238, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 6.946969696969697e-06, | |
| "loss": 0.9291, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 45.77, | |
| "learning_rate": 6.416666666666666e-06, | |
| "loss": 0.938, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 45.77, | |
| "eval_loss": 0.2560683786869049, | |
| "eval_runtime": 110.8197, | |
| "eval_samples_per_second": 30.924, | |
| "eval_steps_per_second": 0.975, | |
| "eval_wer": 0.3117089268557584, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 46.13, | |
| "learning_rate": 5.886363636363636e-06, | |
| "loss": 0.9387, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 5.356060606060605e-06, | |
| "loss": 0.9103, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 46.83, | |
| "learning_rate": 4.825757575757576e-06, | |
| "loss": 0.9283, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 47.18, | |
| "learning_rate": 4.295454545454545e-06, | |
| "loss": 0.9282, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 47.54, | |
| "learning_rate": 3.7651515151515147e-06, | |
| "loss": 0.9168, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 47.89, | |
| "learning_rate": 3.2348484848484844e-06, | |
| "loss": 0.925, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 48.24, | |
| "learning_rate": 2.704545454545454e-06, | |
| "loss": 0.928, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 48.59, | |
| "learning_rate": 2.174242424242424e-06, | |
| "loss": 0.9301, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 48.94, | |
| "learning_rate": 1.6439393939393937e-06, | |
| "loss": 0.9404, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 1.1136363636363635e-06, | |
| "loss": 0.921, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "eval_loss": 0.2559361755847931, | |
| "eval_runtime": 110.0973, | |
| "eval_samples_per_second": 31.127, | |
| "eval_steps_per_second": 0.981, | |
| "eval_wer": 0.31154183549855885, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 49.65, | |
| "learning_rate": 5.833333333333333e-07, | |
| "loss": 0.9243, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 5.303030303030303e-08, | |
| "loss": 0.9223, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 14200, | |
| "total_flos": 5.595667068571877e+19, | |
| "train_loss": 1.318804485697142, | |
| "train_runtime": 22379.119, | |
| "train_samples_per_second": 20.269, | |
| "train_steps_per_second": 0.635 | |
| } | |
| ], | |
| "max_steps": 14200, | |
| "num_train_epochs": 50, | |
| "total_flos": 5.595667068571877e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |