|
{ |
|
"best_metric": 0.8958114385604858, |
|
"best_model_checkpoint": "/dbfs/FileStore/Iskaj/Models/VP_CGN_40EP_To_60EP/checkpoint-1600", |
|
"epoch": 19.623891497130934, |
|
"global_step": 18800, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.973903966597077e-05, |
|
"loss": 0.0836, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.947807933194155e-05, |
|
"loss": 0.0835, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 9.921711899791232e-05, |
|
"loss": 0.0815, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 9.895615866388309e-05, |
|
"loss": 0.0777, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 9.869519832985387e-05, |
|
"loss": 0.0852, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 9.843423799582464e-05, |
|
"loss": 0.0747, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 9.817327766179542e-05, |
|
"loss": 0.079, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 9.791231732776618e-05, |
|
"loss": 0.0776, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"eval_loss": 0.9396540522575378, |
|
"eval_runtime": 2420.5437, |
|
"eval_samples_per_second": 9.084, |
|
"eval_steps_per_second": 1.136, |
|
"eval_wer": 0.20953813057031215, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 9.765135699373696e-05, |
|
"loss": 0.0793, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.739039665970773e-05, |
|
"loss": 0.079, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 9.712943632567851e-05, |
|
"loss": 0.0723, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 9.686847599164928e-05, |
|
"loss": 0.0749, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 9.660751565762006e-05, |
|
"loss": 0.0694, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 9.634655532359081e-05, |
|
"loss": 0.0765, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 9.608559498956159e-05, |
|
"loss": 0.0655, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 9.582463465553236e-05, |
|
"loss": 0.0663, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 0.9835959672927856, |
|
"eval_runtime": 2404.5796, |
|
"eval_samples_per_second": 9.144, |
|
"eval_steps_per_second": 1.143, |
|
"eval_wer": 0.2107740264301708, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 9.556367432150314e-05, |
|
"loss": 0.0752, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 9.530271398747391e-05, |
|
"loss": 0.0814, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 9.504175365344468e-05, |
|
"loss": 0.0747, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 9.478079331941545e-05, |
|
"loss": 0.0686, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 9.451983298538623e-05, |
|
"loss": 0.0761, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 9.4258872651357e-05, |
|
"loss": 0.0695, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 9.399791231732778e-05, |
|
"loss": 0.0659, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 9.373695198329853e-05, |
|
"loss": 0.0765, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 0.9291716814041138, |
|
"eval_runtime": 2388.9228, |
|
"eval_samples_per_second": 9.204, |
|
"eval_steps_per_second": 1.151, |
|
"eval_wer": 0.21025595995960839, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 9.347599164926931e-05, |
|
"loss": 0.0735, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 9.321503131524008e-05, |
|
"loss": 0.0734, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 9.295407098121086e-05, |
|
"loss": 0.0674, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 9.269311064718163e-05, |
|
"loss": 0.0669, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 9.243215031315241e-05, |
|
"loss": 0.0689, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 9.217118997912317e-05, |
|
"loss": 0.0702, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 9.191022964509395e-05, |
|
"loss": 0.0765, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 9.164926931106472e-05, |
|
"loss": 0.0757, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"eval_loss": 0.8958114385604858, |
|
"eval_runtime": 2362.4608, |
|
"eval_samples_per_second": 9.307, |
|
"eval_steps_per_second": 1.164, |
|
"eval_wer": 0.20942398033103568, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 9.13883089770355e-05, |
|
"loss": 0.0752, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 9.112734864300627e-05, |
|
"loss": 0.0725, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 9.086638830897703e-05, |
|
"loss": 0.0669, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 9.060542797494782e-05, |
|
"loss": 0.0699, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 9.034446764091858e-05, |
|
"loss": 0.0723, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 9.008350730688935e-05, |
|
"loss": 0.0712, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 8.982254697286013e-05, |
|
"loss": 0.0728, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 8.95615866388309e-05, |
|
"loss": 0.0655, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"eval_loss": 0.9281134605407715, |
|
"eval_runtime": 2378.3708, |
|
"eval_samples_per_second": 9.245, |
|
"eval_steps_per_second": 1.156, |
|
"eval_wer": 0.20970277033849935, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 8.930062630480167e-05, |
|
"loss": 0.068, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 8.903966597077245e-05, |
|
"loss": 0.0645, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 8.877870563674322e-05, |
|
"loss": 0.0665, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 8.8517745302714e-05, |
|
"loss": 0.0648, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 8.825678496868477e-05, |
|
"loss": 0.0629, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 8.799582463465554e-05, |
|
"loss": 0.0643, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 8.77348643006263e-05, |
|
"loss": 0.0601, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 8.747390396659709e-05, |
|
"loss": 0.0686, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"eval_loss": 0.9298621416091919, |
|
"eval_runtime": 2386.5283, |
|
"eval_samples_per_second": 9.213, |
|
"eval_steps_per_second": 1.152, |
|
"eval_wer": 0.2079092944637134, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 8.721294363256785e-05, |
|
"loss": 0.0637, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 8.695198329853864e-05, |
|
"loss": 0.0675, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 8.669102296450939e-05, |
|
"loss": 0.0719, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 8.643006263048017e-05, |
|
"loss": 0.0709, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 8.616910229645094e-05, |
|
"loss": 0.0702, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 8.590814196242172e-05, |
|
"loss": 0.0645, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 8.564718162839249e-05, |
|
"loss": 0.0707, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 8.538622129436326e-05, |
|
"loss": 0.0644, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"eval_loss": 1.0021286010742188, |
|
"eval_runtime": 2368.1778, |
|
"eval_samples_per_second": 9.285, |
|
"eval_steps_per_second": 1.161, |
|
"eval_wer": 0.20971374632304518, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 8.512526096033403e-05, |
|
"loss": 0.0657, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 8.486430062630481e-05, |
|
"loss": 0.0721, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 8.460334029227558e-05, |
|
"loss": 0.067, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"learning_rate": 8.434237995824636e-05, |
|
"loss": 0.0724, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 8.408141962421713e-05, |
|
"loss": 0.0666, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 8.38204592901879e-05, |
|
"loss": 0.0618, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 8.355949895615866e-05, |
|
"loss": 0.0649, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 8.329853862212944e-05, |
|
"loss": 0.065, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"eval_loss": 0.9249215722084045, |
|
"eval_runtime": 2321.5241, |
|
"eval_samples_per_second": 9.471, |
|
"eval_steps_per_second": 1.184, |
|
"eval_wer": 0.2105676779207095, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 8.303757828810021e-05, |
|
"loss": 0.0586, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 8.277661795407099e-05, |
|
"loss": 0.0683, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 8.251565762004175e-05, |
|
"loss": 0.0645, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 8.225469728601253e-05, |
|
"loss": 0.0655, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 8.19937369519833e-05, |
|
"loss": 0.0634, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 8.173277661795408e-05, |
|
"loss": 0.0726, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 8.147181628392485e-05, |
|
"loss": 0.0676, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 8.121085594989561e-05, |
|
"loss": 0.066, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"eval_loss": 0.97150719165802, |
|
"eval_runtime": 2307.8466, |
|
"eval_samples_per_second": 9.527, |
|
"eval_steps_per_second": 1.191, |
|
"eval_wer": 0.20944812749703648, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 8.09498956158664e-05, |
|
"loss": 0.0621, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 8.068893528183716e-05, |
|
"loss": 0.061, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 8.042797494780793e-05, |
|
"loss": 0.0667, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"learning_rate": 8.016701461377871e-05, |
|
"loss": 0.0635, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 7.990605427974948e-05, |
|
"loss": 0.0597, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 7.964509394572025e-05, |
|
"loss": 0.0583, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 7.938413361169103e-05, |
|
"loss": 0.0626, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 7.91231732776618e-05, |
|
"loss": 0.0629, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"eval_loss": 1.020053505897522, |
|
"eval_runtime": 2289.6794, |
|
"eval_samples_per_second": 9.603, |
|
"eval_steps_per_second": 1.201, |
|
"eval_wer": 0.2082912587259077, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 7.886221294363258e-05, |
|
"loss": 0.0615, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 7.860125260960335e-05, |
|
"loss": 0.0576, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 7.834029227557412e-05, |
|
"loss": 0.0633, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 7.807933194154488e-05, |
|
"loss": 0.0596, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 7.781837160751567e-05, |
|
"loss": 0.0637, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 7.755741127348643e-05, |
|
"loss": 0.0627, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 7.729645093945722e-05, |
|
"loss": 0.0581, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 7.703549060542797e-05, |
|
"loss": 0.056, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"eval_loss": 1.0113539695739746, |
|
"eval_runtime": 2285.7115, |
|
"eval_samples_per_second": 9.62, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20872371251701277, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 7.677974947807933e-05, |
|
"loss": 0.0606, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 7.65187891440501e-05, |
|
"loss": 0.0649, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 7.625782881002088e-05, |
|
"loss": 0.0601, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 7.599686847599165e-05, |
|
"loss": 0.0643, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 7.573590814196243e-05, |
|
"loss": 0.0628, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 7.547494780793319e-05, |
|
"loss": 0.0559, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 7.521398747390397e-05, |
|
"loss": 0.0652, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 7.495302713987474e-05, |
|
"loss": 0.0642, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"eval_loss": 0.962189793586731, |
|
"eval_runtime": 2298.4209, |
|
"eval_samples_per_second": 9.567, |
|
"eval_steps_per_second": 1.196, |
|
"eval_wer": 0.20767001800061466, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 5.06, |
|
"learning_rate": 7.469206680584552e-05, |
|
"loss": 0.0624, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 5.11, |
|
"learning_rate": 7.443110647181629e-05, |
|
"loss": 0.0524, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 5.17, |
|
"learning_rate": 7.417014613778706e-05, |
|
"loss": 0.0578, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 5.22, |
|
"learning_rate": 7.390918580375782e-05, |
|
"loss": 0.0649, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 5.27, |
|
"learning_rate": 7.36482254697286e-05, |
|
"loss": 0.0628, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 5.32, |
|
"learning_rate": 7.338726513569937e-05, |
|
"loss": 0.0619, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 5.38, |
|
"learning_rate": 7.312630480167015e-05, |
|
"loss": 0.0549, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 7.286534446764092e-05, |
|
"loss": 0.0621, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"eval_loss": 1.0184942483901978, |
|
"eval_runtime": 2291.4008, |
|
"eval_samples_per_second": 9.596, |
|
"eval_steps_per_second": 1.2, |
|
"eval_wer": 0.20862492865610044, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 5.48, |
|
"learning_rate": 7.260438413361169e-05, |
|
"loss": 0.0536, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 7.234342379958247e-05, |
|
"loss": 0.0567, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 5.58, |
|
"learning_rate": 7.208246346555324e-05, |
|
"loss": 0.0595, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 5.64, |
|
"learning_rate": 7.182150313152402e-05, |
|
"loss": 0.0582, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 7.156054279749479e-05, |
|
"loss": 0.0578, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 5.74, |
|
"learning_rate": 7.129958246346556e-05, |
|
"loss": 0.0623, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 7.103862212943633e-05, |
|
"loss": 0.0547, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 5.85, |
|
"learning_rate": 7.077766179540711e-05, |
|
"loss": 0.0579, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 5.85, |
|
"eval_loss": 1.0210742950439453, |
|
"eval_runtime": 2297.4069, |
|
"eval_samples_per_second": 9.571, |
|
"eval_steps_per_second": 1.197, |
|
"eval_wer": 0.2089103042542916, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 7.051670146137788e-05, |
|
"loss": 0.06, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 5.95, |
|
"learning_rate": 7.025574112734866e-05, |
|
"loss": 0.0559, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 6.999478079331941e-05, |
|
"loss": 0.0618, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 6.05, |
|
"learning_rate": 6.973382045929019e-05, |
|
"loss": 0.057, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 6.947286012526096e-05, |
|
"loss": 0.0611, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 6.16, |
|
"learning_rate": 6.921189979123174e-05, |
|
"loss": 0.0585, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 6.21, |
|
"learning_rate": 6.895093945720251e-05, |
|
"loss": 0.051, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"learning_rate": 6.868997912317328e-05, |
|
"loss": 0.055, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"eval_loss": 1.0093300342559814, |
|
"eval_runtime": 2290.7926, |
|
"eval_samples_per_second": 9.598, |
|
"eval_steps_per_second": 1.2, |
|
"eval_wer": 0.20797734556789743, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 6.32, |
|
"learning_rate": 6.842901878914405e-05, |
|
"loss": 0.0519, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 6.37, |
|
"learning_rate": 6.816805845511483e-05, |
|
"loss": 0.056, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 6.42, |
|
"learning_rate": 6.79070981210856e-05, |
|
"loss": 0.0584, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 6.47, |
|
"learning_rate": 6.764613778705638e-05, |
|
"loss": 0.061, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 6.738517745302715e-05, |
|
"loss": 0.0547, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 6.58, |
|
"learning_rate": 6.712421711899791e-05, |
|
"loss": 0.0593, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 6.63, |
|
"learning_rate": 6.686325678496868e-05, |
|
"loss": 0.0592, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 6.660229645093946e-05, |
|
"loss": 0.0575, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"eval_loss": 0.9511479139328003, |
|
"eval_runtime": 2297.8339, |
|
"eval_samples_per_second": 9.569, |
|
"eval_steps_per_second": 1.196, |
|
"eval_wer": 0.20716951310532555, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 6.73, |
|
"learning_rate": 6.634133611691023e-05, |
|
"loss": 0.0616, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"learning_rate": 6.608037578288101e-05, |
|
"loss": 0.0569, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"learning_rate": 6.581941544885177e-05, |
|
"loss": 0.0559, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"learning_rate": 6.555845511482255e-05, |
|
"loss": 0.058, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"learning_rate": 6.529749478079332e-05, |
|
"loss": 0.0584, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 6.99, |
|
"learning_rate": 6.50365344467641e-05, |
|
"loss": 0.0589, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 6.477557411273487e-05, |
|
"loss": 0.0521, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 7.1, |
|
"learning_rate": 6.451461377870563e-05, |
|
"loss": 0.0537, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 7.1, |
|
"eval_loss": 1.0872694253921509, |
|
"eval_runtime": 2286.4716, |
|
"eval_samples_per_second": 9.617, |
|
"eval_steps_per_second": 1.202, |
|
"eval_wer": 0.20757123413970233, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 7.15, |
|
"learning_rate": 6.42536534446764e-05, |
|
"loss": 0.0544, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 7.2, |
|
"learning_rate": 6.399269311064718e-05, |
|
"loss": 0.0545, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 6.373173277661795e-05, |
|
"loss": 0.0562, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 7.31, |
|
"learning_rate": 6.347077244258873e-05, |
|
"loss": 0.0564, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 6.32098121085595e-05, |
|
"loss": 0.0528, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 7.41, |
|
"learning_rate": 6.294885177453027e-05, |
|
"loss": 0.0588, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 7.46, |
|
"learning_rate": 6.268789144050105e-05, |
|
"loss": 0.051, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 7.52, |
|
"learning_rate": 6.242693110647182e-05, |
|
"loss": 0.0549, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 7.52, |
|
"eval_loss": 1.0469272136688232, |
|
"eval_runtime": 2282.6191, |
|
"eval_samples_per_second": 9.633, |
|
"eval_steps_per_second": 1.204, |
|
"eval_wer": 0.20716951310532555, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 7.57, |
|
"learning_rate": 6.216597077244259e-05, |
|
"loss": 0.0547, |
|
"step": 7250 |
|
}, |
|
{ |
|
"epoch": 7.62, |
|
"learning_rate": 6.190501043841337e-05, |
|
"loss": 0.0577, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 7.67, |
|
"learning_rate": 6.164405010438414e-05, |
|
"loss": 0.0553, |
|
"step": 7350 |
|
}, |
|
{ |
|
"epoch": 7.72, |
|
"learning_rate": 6.13830897703549e-05, |
|
"loss": 0.058, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 7.78, |
|
"learning_rate": 6.112212943632569e-05, |
|
"loss": 0.056, |
|
"step": 7450 |
|
}, |
|
{ |
|
"epoch": 7.83, |
|
"learning_rate": 6.0861169102296455e-05, |
|
"loss": 0.0512, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 7.88, |
|
"learning_rate": 6.060020876826723e-05, |
|
"loss": 0.0587, |
|
"step": 7550 |
|
}, |
|
{ |
|
"epoch": 7.93, |
|
"learning_rate": 6.033924843423799e-05, |
|
"loss": 0.0559, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 7.93, |
|
"eval_loss": 0.9638180732727051, |
|
"eval_runtime": 2284.7108, |
|
"eval_samples_per_second": 9.624, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20783026737498353, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 7.98, |
|
"learning_rate": 6.0078288100208766e-05, |
|
"loss": 0.0597, |
|
"step": 7650 |
|
}, |
|
{ |
|
"epoch": 8.04, |
|
"learning_rate": 5.981732776617954e-05, |
|
"loss": 0.0531, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 8.09, |
|
"learning_rate": 5.9556367432150315e-05, |
|
"loss": 0.0528, |
|
"step": 7750 |
|
}, |
|
{ |
|
"epoch": 8.14, |
|
"learning_rate": 5.929540709812109e-05, |
|
"loss": 0.0551, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 8.19, |
|
"learning_rate": 5.9034446764091865e-05, |
|
"loss": 0.0507, |
|
"step": 7850 |
|
}, |
|
{ |
|
"epoch": 8.25, |
|
"learning_rate": 5.877348643006263e-05, |
|
"loss": 0.0518, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 8.3, |
|
"learning_rate": 5.85125260960334e-05, |
|
"loss": 0.0534, |
|
"step": 7950 |
|
}, |
|
{ |
|
"epoch": 8.35, |
|
"learning_rate": 5.8251565762004176e-05, |
|
"loss": 0.056, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 8.35, |
|
"eval_loss": 1.0094764232635498, |
|
"eval_runtime": 2282.77, |
|
"eval_samples_per_second": 9.632, |
|
"eval_steps_per_second": 1.204, |
|
"eval_wer": 0.20796417438644246, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 8.4, |
|
"learning_rate": 5.799060542797495e-05, |
|
"loss": 0.0519, |
|
"step": 8050 |
|
}, |
|
{ |
|
"epoch": 8.45, |
|
"learning_rate": 5.7729645093945725e-05, |
|
"loss": 0.0521, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 8.51, |
|
"learning_rate": 5.746868475991649e-05, |
|
"loss": 0.0527, |
|
"step": 8150 |
|
}, |
|
{ |
|
"epoch": 8.56, |
|
"learning_rate": 5.720772442588727e-05, |
|
"loss": 0.0553, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"learning_rate": 5.694676409185804e-05, |
|
"loss": 0.0559, |
|
"step": 8250 |
|
}, |
|
{ |
|
"epoch": 8.66, |
|
"learning_rate": 5.668580375782882e-05, |
|
"loss": 0.0571, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 8.72, |
|
"learning_rate": 5.642484342379959e-05, |
|
"loss": 0.0517, |
|
"step": 8350 |
|
}, |
|
{ |
|
"epoch": 8.77, |
|
"learning_rate": 5.6163883089770354e-05, |
|
"loss": 0.0537, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 8.77, |
|
"eval_loss": 1.101858139038086, |
|
"eval_runtime": 2292.137, |
|
"eval_samples_per_second": 9.593, |
|
"eval_steps_per_second": 1.199, |
|
"eval_wer": 0.20929007331957677, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 8.82, |
|
"learning_rate": 5.590292275574113e-05, |
|
"loss": 0.0544, |
|
"step": 8450 |
|
}, |
|
{ |
|
"epoch": 8.87, |
|
"learning_rate": 5.5641962421711903e-05, |
|
"loss": 0.0519, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 8.92, |
|
"learning_rate": 5.538100208768268e-05, |
|
"loss": 0.0542, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 8.98, |
|
"learning_rate": 5.512004175365345e-05, |
|
"loss": 0.0494, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 9.03, |
|
"learning_rate": 5.4859081419624214e-05, |
|
"loss": 0.0481, |
|
"step": 8650 |
|
}, |
|
{ |
|
"epoch": 9.08, |
|
"learning_rate": 5.459812108559499e-05, |
|
"loss": 0.0554, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 9.13, |
|
"learning_rate": 5.4342379958246346e-05, |
|
"loss": 0.0515, |
|
"step": 8750 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"learning_rate": 5.408141962421712e-05, |
|
"loss": 0.0497, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"eval_loss": 1.110959529876709, |
|
"eval_runtime": 2293.7481, |
|
"eval_samples_per_second": 9.586, |
|
"eval_steps_per_second": 1.198, |
|
"eval_wer": 0.20725073539096456, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 9.24, |
|
"learning_rate": 5.3820459290187896e-05, |
|
"loss": 0.0542, |
|
"step": 8850 |
|
}, |
|
{ |
|
"epoch": 9.29, |
|
"learning_rate": 5.355949895615867e-05, |
|
"loss": 0.0564, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 9.34, |
|
"learning_rate": 5.329853862212943e-05, |
|
"loss": 0.0532, |
|
"step": 8950 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"learning_rate": 5.303757828810021e-05, |
|
"loss": 0.0464, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 9.45, |
|
"learning_rate": 5.277661795407098e-05, |
|
"loss": 0.0509, |
|
"step": 9050 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"learning_rate": 5.2515657620041756e-05, |
|
"loss": 0.0507, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"learning_rate": 5.225469728601253e-05, |
|
"loss": 0.0541, |
|
"step": 9150 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"learning_rate": 5.19937369519833e-05, |
|
"loss": 0.0509, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"eval_loss": 0.994656503200531, |
|
"eval_runtime": 2296.169, |
|
"eval_samples_per_second": 9.576, |
|
"eval_steps_per_second": 1.197, |
|
"eval_wer": 0.20686877112877025, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 9.66, |
|
"learning_rate": 5.1732776617954074e-05, |
|
"loss": 0.0525, |
|
"step": 9250 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 5.147181628392484e-05, |
|
"loss": 0.0517, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 9.76, |
|
"learning_rate": 5.121085594989562e-05, |
|
"loss": 0.0476, |
|
"step": 9350 |
|
}, |
|
{ |
|
"epoch": 9.81, |
|
"learning_rate": 5.094989561586639e-05, |
|
"loss": 0.0517, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 5.068893528183716e-05, |
|
"loss": 0.0453, |
|
"step": 9450 |
|
}, |
|
{ |
|
"epoch": 9.92, |
|
"learning_rate": 5.0427974947807934e-05, |
|
"loss": 0.048, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 9.97, |
|
"learning_rate": 5.016701461377871e-05, |
|
"loss": 0.0475, |
|
"step": 9550 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 4.9906054279749484e-05, |
|
"loss": 0.05, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"eval_loss": 1.0523179769515991, |
|
"eval_runtime": 2296.5421, |
|
"eval_samples_per_second": 9.574, |
|
"eval_steps_per_second": 1.197, |
|
"eval_wer": 0.20557360495236424, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 10.07, |
|
"learning_rate": 4.964509394572025e-05, |
|
"loss": 0.0452, |
|
"step": 9650 |
|
}, |
|
{ |
|
"epoch": 10.13, |
|
"learning_rate": 4.938413361169103e-05, |
|
"loss": 0.0477, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 10.18, |
|
"learning_rate": 4.91231732776618e-05, |
|
"loss": 0.05, |
|
"step": 9750 |
|
}, |
|
{ |
|
"epoch": 10.23, |
|
"learning_rate": 4.886221294363257e-05, |
|
"loss": 0.0426, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 10.28, |
|
"learning_rate": 4.8601252609603344e-05, |
|
"loss": 0.0462, |
|
"step": 9850 |
|
}, |
|
{ |
|
"epoch": 10.33, |
|
"learning_rate": 4.834029227557412e-05, |
|
"loss": 0.0517, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 10.39, |
|
"learning_rate": 4.807933194154489e-05, |
|
"loss": 0.0483, |
|
"step": 9950 |
|
}, |
|
{ |
|
"epoch": 10.44, |
|
"learning_rate": 4.781837160751566e-05, |
|
"loss": 0.0441, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 10.44, |
|
"eval_loss": 1.0726261138916016, |
|
"eval_runtime": 2296.7153, |
|
"eval_samples_per_second": 9.574, |
|
"eval_steps_per_second": 1.197, |
|
"eval_wer": 0.20558897133072837, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 10.49, |
|
"learning_rate": 4.755741127348643e-05, |
|
"loss": 0.05, |
|
"step": 10050 |
|
}, |
|
{ |
|
"epoch": 10.54, |
|
"learning_rate": 4.7296450939457205e-05, |
|
"loss": 0.0494, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 10.59, |
|
"learning_rate": 4.703549060542798e-05, |
|
"loss": 0.0485, |
|
"step": 10150 |
|
}, |
|
{ |
|
"epoch": 10.65, |
|
"learning_rate": 4.677453027139875e-05, |
|
"loss": 0.049, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 10.7, |
|
"learning_rate": 4.651356993736952e-05, |
|
"loss": 0.0466, |
|
"step": 10250 |
|
}, |
|
{ |
|
"epoch": 10.75, |
|
"learning_rate": 4.62526096033403e-05, |
|
"loss": 0.0472, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 10.8, |
|
"learning_rate": 4.5991649269311065e-05, |
|
"loss": 0.0544, |
|
"step": 10350 |
|
}, |
|
{ |
|
"epoch": 10.86, |
|
"learning_rate": 4.573068893528184e-05, |
|
"loss": 0.0456, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 10.86, |
|
"eval_loss": 1.0436075925827026, |
|
"eval_runtime": 2285.586, |
|
"eval_samples_per_second": 9.62, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20674584010185715, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 10.91, |
|
"learning_rate": 4.546972860125261e-05, |
|
"loss": 0.0494, |
|
"step": 10450 |
|
}, |
|
{ |
|
"epoch": 10.96, |
|
"learning_rate": 4.520876826722338e-05, |
|
"loss": 0.0496, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 4.494780793319416e-05, |
|
"loss": 0.0548, |
|
"step": 10550 |
|
}, |
|
{ |
|
"epoch": 11.06, |
|
"learning_rate": 4.4686847599164926e-05, |
|
"loss": 0.045, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 11.12, |
|
"learning_rate": 4.44258872651357e-05, |
|
"loss": 0.0454, |
|
"step": 10650 |
|
}, |
|
{ |
|
"epoch": 11.17, |
|
"learning_rate": 4.417014613778706e-05, |
|
"loss": 0.047, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"learning_rate": 4.390918580375783e-05, |
|
"loss": 0.0457, |
|
"step": 10750 |
|
}, |
|
{ |
|
"epoch": 11.27, |
|
"learning_rate": 4.364822546972861e-05, |
|
"loss": 0.0469, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 11.27, |
|
"eval_loss": 1.102227807044983, |
|
"eval_runtime": 2288.4521, |
|
"eval_samples_per_second": 9.608, |
|
"eval_steps_per_second": 1.201, |
|
"eval_wer": 0.20656144356148748, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 11.33, |
|
"learning_rate": 4.3387265135699376e-05, |
|
"loss": 0.0487, |
|
"step": 10850 |
|
}, |
|
{ |
|
"epoch": 11.38, |
|
"learning_rate": 4.312630480167015e-05, |
|
"loss": 0.0479, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 11.43, |
|
"learning_rate": 4.2865344467640925e-05, |
|
"loss": 0.0476, |
|
"step": 10950 |
|
}, |
|
{ |
|
"epoch": 11.48, |
|
"learning_rate": 4.260438413361169e-05, |
|
"loss": 0.0497, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 11.53, |
|
"learning_rate": 4.234342379958247e-05, |
|
"loss": 0.0487, |
|
"step": 11050 |
|
}, |
|
{ |
|
"epoch": 11.59, |
|
"learning_rate": 4.208246346555324e-05, |
|
"loss": 0.0478, |
|
"step": 11100 |
|
}, |
|
{ |
|
"epoch": 11.64, |
|
"learning_rate": 4.182150313152401e-05, |
|
"loss": 0.0515, |
|
"step": 11150 |
|
}, |
|
{ |
|
"epoch": 11.69, |
|
"learning_rate": 4.1560542797494786e-05, |
|
"loss": 0.0549, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 11.69, |
|
"eval_loss": 1.093299150466919, |
|
"eval_runtime": 2284.3046, |
|
"eval_samples_per_second": 9.626, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20669096017912808, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 11.74, |
|
"learning_rate": 4.1299582463465554e-05, |
|
"loss": 0.0465, |
|
"step": 11250 |
|
}, |
|
{ |
|
"epoch": 11.79, |
|
"learning_rate": 4.103862212943633e-05, |
|
"loss": 0.0426, |
|
"step": 11300 |
|
}, |
|
{ |
|
"epoch": 11.85, |
|
"learning_rate": 4.07776617954071e-05, |
|
"loss": 0.047, |
|
"step": 11350 |
|
}, |
|
{ |
|
"epoch": 11.9, |
|
"learning_rate": 4.051670146137787e-05, |
|
"loss": 0.0492, |
|
"step": 11400 |
|
}, |
|
{ |
|
"epoch": 11.95, |
|
"learning_rate": 4.0255741127348646e-05, |
|
"loss": 0.0506, |
|
"step": 11450 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 3.999478079331942e-05, |
|
"loss": 0.0467, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 12.06, |
|
"learning_rate": 3.973382045929019e-05, |
|
"loss": 0.0501, |
|
"step": 11550 |
|
}, |
|
{ |
|
"epoch": 12.11, |
|
"learning_rate": 3.9472860125260964e-05, |
|
"loss": 0.0452, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 12.11, |
|
"eval_loss": 1.0941613912582397, |
|
"eval_runtime": 2283.0889, |
|
"eval_samples_per_second": 9.631, |
|
"eval_steps_per_second": 1.204, |
|
"eval_wer": 0.20626070158493218, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 12.16, |
|
"learning_rate": 3.921189979123173e-05, |
|
"loss": 0.051, |
|
"step": 11650 |
|
}, |
|
{ |
|
"epoch": 12.21, |
|
"learning_rate": 3.8950939457202506e-05, |
|
"loss": 0.0453, |
|
"step": 11700 |
|
}, |
|
{ |
|
"epoch": 12.26, |
|
"learning_rate": 3.868997912317328e-05, |
|
"loss": 0.0458, |
|
"step": 11750 |
|
}, |
|
{ |
|
"epoch": 12.32, |
|
"learning_rate": 3.842901878914405e-05, |
|
"loss": 0.0462, |
|
"step": 11800 |
|
}, |
|
{ |
|
"epoch": 12.37, |
|
"learning_rate": 3.8168058455114824e-05, |
|
"loss": 0.0466, |
|
"step": 11850 |
|
}, |
|
{ |
|
"epoch": 12.42, |
|
"learning_rate": 3.79070981210856e-05, |
|
"loss": 0.0486, |
|
"step": 11900 |
|
}, |
|
{ |
|
"epoch": 12.47, |
|
"learning_rate": 3.764613778705637e-05, |
|
"loss": 0.0481, |
|
"step": 11950 |
|
}, |
|
{ |
|
"epoch": 12.53, |
|
"learning_rate": 3.738517745302714e-05, |
|
"loss": 0.0456, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 12.53, |
|
"eval_loss": 1.0609982013702393, |
|
"eval_runtime": 2297.0722, |
|
"eval_samples_per_second": 9.572, |
|
"eval_steps_per_second": 1.197, |
|
"eval_wer": 0.20719366027132632, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 12.58, |
|
"learning_rate": 3.712421711899791e-05, |
|
"loss": 0.0476, |
|
"step": 12050 |
|
}, |
|
{ |
|
"epoch": 12.63, |
|
"learning_rate": 3.6863256784968685e-05, |
|
"loss": 0.0479, |
|
"step": 12100 |
|
}, |
|
{ |
|
"epoch": 12.68, |
|
"learning_rate": 3.660229645093946e-05, |
|
"loss": 0.0481, |
|
"step": 12150 |
|
}, |
|
{ |
|
"epoch": 12.73, |
|
"learning_rate": 3.634133611691023e-05, |
|
"loss": 0.0486, |
|
"step": 12200 |
|
}, |
|
{ |
|
"epoch": 12.79, |
|
"learning_rate": 3.6080375782881e-05, |
|
"loss": 0.0457, |
|
"step": 12250 |
|
}, |
|
{ |
|
"epoch": 12.84, |
|
"learning_rate": 3.5824634655532366e-05, |
|
"loss": 0.1915, |
|
"step": 12300 |
|
}, |
|
{ |
|
"epoch": 12.89, |
|
"learning_rate": 3.5563674321503134e-05, |
|
"loss": 0.0439, |
|
"step": 12350 |
|
}, |
|
{ |
|
"epoch": 12.94, |
|
"learning_rate": 3.530271398747391e-05, |
|
"loss": 0.0445, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 12.94, |
|
"eval_loss": 1.0950515270233154, |
|
"eval_runtime": 2287.2126, |
|
"eval_samples_per_second": 9.613, |
|
"eval_steps_per_second": 1.202, |
|
"eval_wer": 0.20619484567765728, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 3.504175365344468e-05, |
|
"loss": 0.0426, |
|
"step": 12450 |
|
}, |
|
{ |
|
"epoch": 13.05, |
|
"learning_rate": 3.478079331941545e-05, |
|
"loss": 0.0435, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 13.1, |
|
"learning_rate": 3.451983298538623e-05, |
|
"loss": 0.0453, |
|
"step": 12550 |
|
}, |
|
{ |
|
"epoch": 13.15, |
|
"learning_rate": 3.4258872651356995e-05, |
|
"loss": 0.0419, |
|
"step": 12600 |
|
}, |
|
{ |
|
"epoch": 13.2, |
|
"learning_rate": 3.399791231732777e-05, |
|
"loss": 0.0476, |
|
"step": 12650 |
|
}, |
|
{ |
|
"epoch": 13.26, |
|
"learning_rate": 3.3736951983298544e-05, |
|
"loss": 0.0457, |
|
"step": 12700 |
|
}, |
|
{ |
|
"epoch": 13.31, |
|
"learning_rate": 3.347599164926931e-05, |
|
"loss": 0.0485, |
|
"step": 12750 |
|
}, |
|
{ |
|
"epoch": 13.36, |
|
"learning_rate": 3.321503131524009e-05, |
|
"loss": 0.0525, |
|
"step": 12800 |
|
}, |
|
{ |
|
"epoch": 13.36, |
|
"eval_loss": 1.1166725158691406, |
|
"eval_runtime": 2280.6976, |
|
"eval_samples_per_second": 9.641, |
|
"eval_steps_per_second": 1.205, |
|
"eval_wer": 0.20630460552311541, |
|
"step": 12800 |
|
}, |
|
{ |
|
"epoch": 13.41, |
|
"learning_rate": 3.2954070981210855e-05, |
|
"loss": 0.0454, |
|
"step": 12850 |
|
}, |
|
{ |
|
"epoch": 13.47, |
|
"learning_rate": 3.269311064718163e-05, |
|
"loss": 0.0441, |
|
"step": 12900 |
|
}, |
|
{ |
|
"epoch": 13.52, |
|
"learning_rate": 3.2432150313152405e-05, |
|
"loss": 0.0458, |
|
"step": 12950 |
|
}, |
|
{ |
|
"epoch": 13.57, |
|
"learning_rate": 3.217118997912317e-05, |
|
"loss": 0.0435, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 13.62, |
|
"learning_rate": 3.191022964509395e-05, |
|
"loss": 0.0404, |
|
"step": 13050 |
|
}, |
|
{ |
|
"epoch": 13.67, |
|
"learning_rate": 3.164926931106472e-05, |
|
"loss": 0.0495, |
|
"step": 13100 |
|
}, |
|
{ |
|
"epoch": 13.73, |
|
"learning_rate": 3.138830897703549e-05, |
|
"loss": 0.0529, |
|
"step": 13150 |
|
}, |
|
{ |
|
"epoch": 13.78, |
|
"learning_rate": 3.1127348643006265e-05, |
|
"loss": 0.0445, |
|
"step": 13200 |
|
}, |
|
{ |
|
"epoch": 13.78, |
|
"eval_loss": 1.1110990047454834, |
|
"eval_runtime": 2281.2238, |
|
"eval_samples_per_second": 9.639, |
|
"eval_steps_per_second": 1.205, |
|
"eval_wer": 0.20564385125345744, |
|
"step": 13200 |
|
}, |
|
{ |
|
"epoch": 13.83, |
|
"learning_rate": 3.086638830897703e-05, |
|
"loss": 0.0412, |
|
"step": 13250 |
|
}, |
|
{ |
|
"epoch": 13.88, |
|
"learning_rate": 3.060542797494781e-05, |
|
"loss": 0.045, |
|
"step": 13300 |
|
}, |
|
{ |
|
"epoch": 13.93, |
|
"learning_rate": 3.0344467640918583e-05, |
|
"loss": 0.0432, |
|
"step": 13350 |
|
}, |
|
{ |
|
"epoch": 13.99, |
|
"learning_rate": 3.008350730688935e-05, |
|
"loss": 0.0439, |
|
"step": 13400 |
|
}, |
|
{ |
|
"epoch": 14.04, |
|
"learning_rate": 2.9822546972860126e-05, |
|
"loss": 0.0458, |
|
"step": 13450 |
|
}, |
|
{ |
|
"epoch": 14.09, |
|
"learning_rate": 2.95615866388309e-05, |
|
"loss": 0.0492, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 14.14, |
|
"learning_rate": 2.9300626304801672e-05, |
|
"loss": 0.0425, |
|
"step": 13550 |
|
}, |
|
{ |
|
"epoch": 14.2, |
|
"learning_rate": 2.9039665970772447e-05, |
|
"loss": 0.0435, |
|
"step": 13600 |
|
}, |
|
{ |
|
"epoch": 14.2, |
|
"eval_loss": 1.131235957145691, |
|
"eval_runtime": 2281.1607, |
|
"eval_samples_per_second": 9.639, |
|
"eval_steps_per_second": 1.205, |
|
"eval_wer": 0.2058567853536462, |
|
"step": 13600 |
|
}, |
|
{ |
|
"epoch": 14.25, |
|
"learning_rate": 2.8778705636743215e-05, |
|
"loss": 0.0429, |
|
"step": 13650 |
|
}, |
|
{ |
|
"epoch": 14.3, |
|
"learning_rate": 2.851774530271399e-05, |
|
"loss": 0.0428, |
|
"step": 13700 |
|
}, |
|
{ |
|
"epoch": 14.35, |
|
"learning_rate": 2.8256784968684764e-05, |
|
"loss": 0.0458, |
|
"step": 13750 |
|
}, |
|
{ |
|
"epoch": 14.4, |
|
"learning_rate": 2.7995824634655532e-05, |
|
"loss": 0.0411, |
|
"step": 13800 |
|
}, |
|
{ |
|
"epoch": 14.46, |
|
"learning_rate": 2.7734864300626307e-05, |
|
"loss": 0.0444, |
|
"step": 13850 |
|
}, |
|
{ |
|
"epoch": 14.51, |
|
"learning_rate": 2.7473903966597082e-05, |
|
"loss": 0.0457, |
|
"step": 13900 |
|
}, |
|
{ |
|
"epoch": 14.56, |
|
"learning_rate": 2.721294363256785e-05, |
|
"loss": 0.042, |
|
"step": 13950 |
|
}, |
|
{ |
|
"epoch": 14.61, |
|
"learning_rate": 2.6951983298538625e-05, |
|
"loss": 0.0448, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 14.61, |
|
"eval_loss": 1.1048628091812134, |
|
"eval_runtime": 2270.1056, |
|
"eval_samples_per_second": 9.686, |
|
"eval_steps_per_second": 1.211, |
|
"eval_wer": 0.2052684725819906, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 14.67, |
|
"learning_rate": 2.6691022964509393e-05, |
|
"loss": 0.0431, |
|
"step": 14050 |
|
}, |
|
{ |
|
"epoch": 14.72, |
|
"learning_rate": 2.6430062630480167e-05, |
|
"loss": 0.0416, |
|
"step": 14100 |
|
}, |
|
{ |
|
"epoch": 14.77, |
|
"learning_rate": 2.6169102296450942e-05, |
|
"loss": 0.0451, |
|
"step": 14150 |
|
}, |
|
{ |
|
"epoch": 14.82, |
|
"learning_rate": 2.590814196242171e-05, |
|
"loss": 0.0432, |
|
"step": 14200 |
|
}, |
|
{ |
|
"epoch": 14.87, |
|
"learning_rate": 2.5647181628392485e-05, |
|
"loss": 0.0457, |
|
"step": 14250 |
|
}, |
|
{ |
|
"epoch": 14.93, |
|
"learning_rate": 2.538622129436326e-05, |
|
"loss": 0.0428, |
|
"step": 14300 |
|
}, |
|
{ |
|
"epoch": 14.98, |
|
"learning_rate": 2.5125260960334028e-05, |
|
"loss": 0.0437, |
|
"step": 14350 |
|
}, |
|
{ |
|
"epoch": 15.03, |
|
"learning_rate": 2.4864300626304803e-05, |
|
"loss": 0.0439, |
|
"step": 14400 |
|
}, |
|
{ |
|
"epoch": 15.03, |
|
"eval_loss": 1.11318838596344, |
|
"eval_runtime": 2284.6428, |
|
"eval_samples_per_second": 9.624, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.2054462835316328, |
|
"step": 14400 |
|
}, |
|
{ |
|
"epoch": 15.08, |
|
"learning_rate": 2.4603340292275574e-05, |
|
"loss": 0.0444, |
|
"step": 14450 |
|
}, |
|
{ |
|
"epoch": 15.14, |
|
"learning_rate": 2.434237995824635e-05, |
|
"loss": 0.0484, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 15.19, |
|
"learning_rate": 2.408141962421712e-05, |
|
"loss": 0.0457, |
|
"step": 14550 |
|
}, |
|
{ |
|
"epoch": 15.24, |
|
"learning_rate": 2.3820459290187895e-05, |
|
"loss": 0.0398, |
|
"step": 14600 |
|
}, |
|
{ |
|
"epoch": 15.29, |
|
"learning_rate": 2.3559498956158667e-05, |
|
"loss": 0.0409, |
|
"step": 14650 |
|
}, |
|
{ |
|
"epoch": 15.34, |
|
"learning_rate": 2.3298538622129438e-05, |
|
"loss": 0.0464, |
|
"step": 14700 |
|
}, |
|
{ |
|
"epoch": 15.4, |
|
"learning_rate": 2.303757828810021e-05, |
|
"loss": 0.0395, |
|
"step": 14750 |
|
}, |
|
{ |
|
"epoch": 15.45, |
|
"learning_rate": 2.2776617954070984e-05, |
|
"loss": 0.0436, |
|
"step": 14800 |
|
}, |
|
{ |
|
"epoch": 15.45, |
|
"eval_loss": 1.1486200094223022, |
|
"eval_runtime": 2280.6212, |
|
"eval_samples_per_second": 9.641, |
|
"eval_steps_per_second": 1.205, |
|
"eval_wer": 0.20591386047328444, |
|
"step": 14800 |
|
}, |
|
{ |
|
"epoch": 15.5, |
|
"learning_rate": 2.2515657620041756e-05, |
|
"loss": 0.0413, |
|
"step": 14850 |
|
}, |
|
{ |
|
"epoch": 15.55, |
|
"learning_rate": 2.2254697286012527e-05, |
|
"loss": 0.0392, |
|
"step": 14900 |
|
}, |
|
{ |
|
"epoch": 15.61, |
|
"learning_rate": 2.19937369519833e-05, |
|
"loss": 0.0406, |
|
"step": 14950 |
|
}, |
|
{ |
|
"epoch": 15.66, |
|
"learning_rate": 2.1732776617954073e-05, |
|
"loss": 0.0419, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 15.71, |
|
"learning_rate": 2.1471816283924845e-05, |
|
"loss": 0.0451, |
|
"step": 15050 |
|
}, |
|
{ |
|
"epoch": 15.76, |
|
"learning_rate": 2.1210855949895616e-05, |
|
"loss": 0.0454, |
|
"step": 15100 |
|
}, |
|
{ |
|
"epoch": 15.81, |
|
"learning_rate": 2.0949895615866387e-05, |
|
"loss": 0.042, |
|
"step": 15150 |
|
}, |
|
{ |
|
"epoch": 15.87, |
|
"learning_rate": 2.0688935281837162e-05, |
|
"loss": 0.043, |
|
"step": 15200 |
|
}, |
|
{ |
|
"epoch": 15.87, |
|
"eval_loss": 1.1113590002059937, |
|
"eval_runtime": 2271.0619, |
|
"eval_samples_per_second": 9.682, |
|
"eval_steps_per_second": 1.21, |
|
"eval_wer": 0.20565482723800324, |
|
"step": 15200 |
|
}, |
|
{ |
|
"epoch": 15.92, |
|
"learning_rate": 2.0427974947807934e-05, |
|
"loss": 0.0384, |
|
"step": 15250 |
|
}, |
|
{ |
|
"epoch": 15.97, |
|
"learning_rate": 2.0167014613778705e-05, |
|
"loss": 0.0461, |
|
"step": 15300 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 1.9906054279749476e-05, |
|
"loss": 0.0414, |
|
"step": 15350 |
|
}, |
|
{ |
|
"epoch": 16.08, |
|
"learning_rate": 1.964509394572025e-05, |
|
"loss": 0.0398, |
|
"step": 15400 |
|
}, |
|
{ |
|
"epoch": 16.13, |
|
"learning_rate": 1.9384133611691023e-05, |
|
"loss": 0.0391, |
|
"step": 15450 |
|
}, |
|
{ |
|
"epoch": 16.18, |
|
"learning_rate": 1.9123173277661798e-05, |
|
"loss": 0.0398, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 16.23, |
|
"learning_rate": 1.886221294363257e-05, |
|
"loss": 0.0454, |
|
"step": 15550 |
|
}, |
|
{ |
|
"epoch": 16.28, |
|
"learning_rate": 1.8601252609603344e-05, |
|
"loss": 0.046, |
|
"step": 15600 |
|
}, |
|
{ |
|
"epoch": 16.28, |
|
"eval_loss": 1.1185530424118042, |
|
"eval_runtime": 2277.3852, |
|
"eval_samples_per_second": 9.655, |
|
"eval_steps_per_second": 1.207, |
|
"eval_wer": 0.2055275058172718, |
|
"step": 15600 |
|
}, |
|
{ |
|
"epoch": 16.34, |
|
"learning_rate": 1.8340292275574115e-05, |
|
"loss": 0.0391, |
|
"step": 15650 |
|
}, |
|
{ |
|
"epoch": 16.39, |
|
"learning_rate": 1.8079331941544887e-05, |
|
"loss": 0.0443, |
|
"step": 15700 |
|
}, |
|
{ |
|
"epoch": 16.44, |
|
"learning_rate": 1.7818371607515658e-05, |
|
"loss": 0.0424, |
|
"step": 15750 |
|
}, |
|
{ |
|
"epoch": 16.49, |
|
"learning_rate": 1.7557411273486433e-05, |
|
"loss": 0.0455, |
|
"step": 15800 |
|
}, |
|
{ |
|
"epoch": 16.54, |
|
"learning_rate": 1.7296450939457204e-05, |
|
"loss": 0.0415, |
|
"step": 15850 |
|
}, |
|
{ |
|
"epoch": 16.6, |
|
"learning_rate": 1.7035490605427976e-05, |
|
"loss": 0.0427, |
|
"step": 15900 |
|
}, |
|
{ |
|
"epoch": 16.65, |
|
"learning_rate": 1.6774530271398747e-05, |
|
"loss": 0.0428, |
|
"step": 15950 |
|
}, |
|
{ |
|
"epoch": 16.7, |
|
"learning_rate": 1.6513569937369522e-05, |
|
"loss": 0.0432, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 16.7, |
|
"eval_loss": 1.1420904397964478, |
|
"eval_runtime": 2286.2257, |
|
"eval_samples_per_second": 9.618, |
|
"eval_steps_per_second": 1.202, |
|
"eval_wer": 0.20530579092944637, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 16.75, |
|
"learning_rate": 1.6252609603340293e-05, |
|
"loss": 0.0434, |
|
"step": 16050 |
|
}, |
|
{ |
|
"epoch": 16.81, |
|
"learning_rate": 1.5991649269311065e-05, |
|
"loss": 0.0422, |
|
"step": 16100 |
|
}, |
|
{ |
|
"epoch": 16.86, |
|
"learning_rate": 1.5730688935281836e-05, |
|
"loss": 0.0435, |
|
"step": 16150 |
|
}, |
|
{ |
|
"epoch": 16.91, |
|
"learning_rate": 1.546972860125261e-05, |
|
"loss": 0.0423, |
|
"step": 16200 |
|
}, |
|
{ |
|
"epoch": 16.96, |
|
"learning_rate": 1.5208768267223384e-05, |
|
"loss": 0.0453, |
|
"step": 16250 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 1.4947807933194155e-05, |
|
"loss": 0.0401, |
|
"step": 16300 |
|
}, |
|
{ |
|
"epoch": 17.07, |
|
"learning_rate": 1.4686847599164927e-05, |
|
"loss": 0.0435, |
|
"step": 16350 |
|
}, |
|
{ |
|
"epoch": 17.12, |
|
"learning_rate": 1.4425887265135702e-05, |
|
"loss": 0.0403, |
|
"step": 16400 |
|
}, |
|
{ |
|
"epoch": 17.12, |
|
"eval_loss": 1.1468006372451782, |
|
"eval_runtime": 2284.2746, |
|
"eval_samples_per_second": 9.626, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20491065548579707, |
|
"step": 16400 |
|
}, |
|
{ |
|
"epoch": 17.17, |
|
"learning_rate": 1.4164926931106473e-05, |
|
"loss": 0.0397, |
|
"step": 16450 |
|
}, |
|
{ |
|
"epoch": 17.22, |
|
"learning_rate": 1.3903966597077244e-05, |
|
"loss": 0.0375, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 17.28, |
|
"learning_rate": 1.3643006263048016e-05, |
|
"loss": 0.0424, |
|
"step": 16550 |
|
}, |
|
{ |
|
"epoch": 17.33, |
|
"learning_rate": 1.338204592901879e-05, |
|
"loss": 0.0438, |
|
"step": 16600 |
|
}, |
|
{ |
|
"epoch": 17.38, |
|
"learning_rate": 1.3121085594989562e-05, |
|
"loss": 0.0385, |
|
"step": 16650 |
|
}, |
|
{ |
|
"epoch": 17.43, |
|
"learning_rate": 1.2860125260960335e-05, |
|
"loss": 0.0402, |
|
"step": 16700 |
|
}, |
|
{ |
|
"epoch": 17.48, |
|
"learning_rate": 1.2599164926931107e-05, |
|
"loss": 0.0457, |
|
"step": 16750 |
|
}, |
|
{ |
|
"epoch": 17.54, |
|
"learning_rate": 1.233820459290188e-05, |
|
"loss": 0.0426, |
|
"step": 16800 |
|
}, |
|
{ |
|
"epoch": 17.54, |
|
"eval_loss": 1.149783730506897, |
|
"eval_runtime": 2292.0315, |
|
"eval_samples_per_second": 9.593, |
|
"eval_steps_per_second": 1.199, |
|
"eval_wer": 0.2040084295561312, |
|
"step": 16800 |
|
}, |
|
{ |
|
"epoch": 17.59, |
|
"learning_rate": 1.2077244258872653e-05, |
|
"loss": 0.0387, |
|
"step": 16850 |
|
}, |
|
{ |
|
"epoch": 17.64, |
|
"learning_rate": 1.1816283924843424e-05, |
|
"loss": 0.0399, |
|
"step": 16900 |
|
}, |
|
{ |
|
"epoch": 17.69, |
|
"learning_rate": 1.1555323590814197e-05, |
|
"loss": 0.0412, |
|
"step": 16950 |
|
}, |
|
{ |
|
"epoch": 17.74, |
|
"learning_rate": 1.1294363256784969e-05, |
|
"loss": 0.041, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 17.8, |
|
"learning_rate": 1.1033402922755742e-05, |
|
"loss": 0.0401, |
|
"step": 17050 |
|
}, |
|
{ |
|
"epoch": 17.85, |
|
"learning_rate": 1.0772442588726513e-05, |
|
"loss": 0.0422, |
|
"step": 17100 |
|
}, |
|
{ |
|
"epoch": 17.9, |
|
"learning_rate": 1.0511482254697288e-05, |
|
"loss": 0.0384, |
|
"step": 17150 |
|
}, |
|
{ |
|
"epoch": 17.95, |
|
"learning_rate": 1.025052192066806e-05, |
|
"loss": 0.0367, |
|
"step": 17200 |
|
}, |
|
{ |
|
"epoch": 17.95, |
|
"eval_loss": 1.1410751342773438, |
|
"eval_runtime": 2289.1143, |
|
"eval_samples_per_second": 9.605, |
|
"eval_steps_per_second": 1.201, |
|
"eval_wer": 0.20410501822013435, |
|
"step": 17200 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 9.989561586638832e-06, |
|
"loss": 0.0424, |
|
"step": 17250 |
|
}, |
|
{ |
|
"epoch": 18.06, |
|
"learning_rate": 9.728601252609604e-06, |
|
"loss": 0.0362, |
|
"step": 17300 |
|
}, |
|
{ |
|
"epoch": 18.11, |
|
"learning_rate": 9.467640918580377e-06, |
|
"loss": 0.0418, |
|
"step": 17350 |
|
}, |
|
{ |
|
"epoch": 18.16, |
|
"learning_rate": 9.206680584551148e-06, |
|
"loss": 0.0423, |
|
"step": 17400 |
|
}, |
|
{ |
|
"epoch": 18.21, |
|
"learning_rate": 8.945720250521922e-06, |
|
"loss": 0.0403, |
|
"step": 17450 |
|
}, |
|
{ |
|
"epoch": 18.27, |
|
"learning_rate": 8.684759916492693e-06, |
|
"loss": 0.0429, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 18.32, |
|
"learning_rate": 8.423799582463466e-06, |
|
"loss": 0.0377, |
|
"step": 17550 |
|
}, |
|
{ |
|
"epoch": 18.37, |
|
"learning_rate": 8.162839248434239e-06, |
|
"loss": 0.0398, |
|
"step": 17600 |
|
}, |
|
{ |
|
"epoch": 18.37, |
|
"eval_loss": 1.1493802070617676, |
|
"eval_runtime": 2285.3013, |
|
"eval_samples_per_second": 9.621, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20455942398033103, |
|
"step": 17600 |
|
}, |
|
{ |
|
"epoch": 18.42, |
|
"learning_rate": 7.901878914405012e-06, |
|
"loss": 0.041, |
|
"step": 17650 |
|
}, |
|
{ |
|
"epoch": 18.48, |
|
"learning_rate": 7.640918580375784e-06, |
|
"loss": 0.0453, |
|
"step": 17700 |
|
}, |
|
{ |
|
"epoch": 18.53, |
|
"learning_rate": 7.379958246346557e-06, |
|
"loss": 0.0404, |
|
"step": 17750 |
|
}, |
|
{ |
|
"epoch": 18.58, |
|
"learning_rate": 7.118997912317328e-06, |
|
"loss": 0.0456, |
|
"step": 17800 |
|
}, |
|
{ |
|
"epoch": 18.63, |
|
"learning_rate": 6.858037578288101e-06, |
|
"loss": 0.0411, |
|
"step": 17850 |
|
}, |
|
{ |
|
"epoch": 18.68, |
|
"learning_rate": 6.597077244258873e-06, |
|
"loss": 0.0441, |
|
"step": 17900 |
|
}, |
|
{ |
|
"epoch": 18.74, |
|
"learning_rate": 6.336116910229645e-06, |
|
"loss": 0.0429, |
|
"step": 17950 |
|
}, |
|
{ |
|
"epoch": 18.79, |
|
"learning_rate": 6.075156576200418e-06, |
|
"loss": 0.037, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 18.79, |
|
"eval_loss": 1.1569510698318481, |
|
"eval_runtime": 2284.6736, |
|
"eval_samples_per_second": 9.624, |
|
"eval_steps_per_second": 1.203, |
|
"eval_wer": 0.20445844492250956, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 18.84, |
|
"learning_rate": 5.81419624217119e-06, |
|
"loss": 0.0359, |
|
"step": 18050 |
|
}, |
|
{ |
|
"epoch": 18.89, |
|
"learning_rate": 5.553235908141963e-06, |
|
"loss": 0.0395, |
|
"step": 18100 |
|
}, |
|
{ |
|
"epoch": 18.95, |
|
"learning_rate": 5.29749478079332e-06, |
|
"loss": 0.0445, |
|
"step": 18150 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"learning_rate": 5.036534446764092e-06, |
|
"loss": 0.0422, |
|
"step": 18200 |
|
}, |
|
{ |
|
"epoch": 19.05, |
|
"learning_rate": 4.775574112734864e-06, |
|
"loss": 0.0343, |
|
"step": 18250 |
|
}, |
|
{ |
|
"epoch": 19.1, |
|
"learning_rate": 4.514613778705637e-06, |
|
"loss": 0.0409, |
|
"step": 18300 |
|
}, |
|
{ |
|
"epoch": 19.15, |
|
"learning_rate": 4.25365344467641e-06, |
|
"loss": 0.041, |
|
"step": 18350 |
|
}, |
|
{ |
|
"epoch": 19.21, |
|
"learning_rate": 3.992693110647182e-06, |
|
"loss": 0.0383, |
|
"step": 18400 |
|
}, |
|
{ |
|
"epoch": 19.21, |
|
"eval_loss": 1.1532527208328247, |
|
"eval_runtime": 2289.8513, |
|
"eval_samples_per_second": 9.602, |
|
"eval_steps_per_second": 1.201, |
|
"eval_wer": 0.2042784387759582, |
|
"step": 18400 |
|
}, |
|
{ |
|
"epoch": 19.26, |
|
"learning_rate": 3.7317327766179542e-06, |
|
"loss": 0.0427, |
|
"step": 18450 |
|
}, |
|
{ |
|
"epoch": 19.31, |
|
"learning_rate": 3.4707724425887265e-06, |
|
"loss": 0.0391, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 19.36, |
|
"learning_rate": 3.209812108559499e-06, |
|
"loss": 0.0351, |
|
"step": 18550 |
|
}, |
|
{ |
|
"epoch": 19.42, |
|
"learning_rate": 2.9488517745302714e-06, |
|
"loss": 0.037, |
|
"step": 18600 |
|
}, |
|
{ |
|
"epoch": 19.47, |
|
"learning_rate": 2.687891440501044e-06, |
|
"loss": 0.0423, |
|
"step": 18650 |
|
}, |
|
{ |
|
"epoch": 19.52, |
|
"learning_rate": 2.4269311064718164e-06, |
|
"loss": 0.0434, |
|
"step": 18700 |
|
}, |
|
{ |
|
"epoch": 19.57, |
|
"learning_rate": 2.165970772442589e-06, |
|
"loss": 0.0435, |
|
"step": 18750 |
|
}, |
|
{ |
|
"epoch": 19.62, |
|
"learning_rate": 1.9050104384133613e-06, |
|
"loss": 0.0374, |
|
"step": 18800 |
|
}, |
|
{ |
|
"epoch": 19.62, |
|
"eval_loss": 1.1447900533676147, |
|
"eval_runtime": 2296.5158, |
|
"eval_samples_per_second": 9.575, |
|
"eval_steps_per_second": 1.197, |
|
"eval_wer": 0.20419941168722835, |
|
"step": 18800 |
|
} |
|
], |
|
"max_steps": 19160, |
|
"num_train_epochs": 20, |
|
"total_flos": 1.280273400848764e+20, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|