| { |
| "best_metric": 0.04629843682050705, |
| "best_model_checkpoint": "/scratch/lingjzhu_root/lingjzhu1/lingjzhu/g2p/byt5_small_finetuned_from_pretrained/checkpoint-125000", |
| "epoch": 9.917799364213547, |
| "global_step": 140000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.0003, |
| "loss": 1.3905, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0002999623214094654, |
| "loss": 0.2662, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0002998493045668776, |
| "loss": 0.185, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00029966100624977436, |
| "loss": 0.1523, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00029939752105569156, |
| "loss": 0.1309, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_cer": 0.15177127579292352, |
| "eval_loss": 0.15828794240951538, |
| "eval_runtime": 99.5729, |
| "eval_samples_per_second": 50.214, |
| "eval_steps_per_second": 0.402, |
| "eval_wer": 0.4034, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00029905898135463893, |
| "loss": 0.1159, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0002986455572226002, |
| "loss": 0.1057, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00029815745635609, |
| "loss": 0.0972, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00029759492396781067, |
| "loss": 0.0899, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00029695824266346256, |
| "loss": 0.0849, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.71, |
| "eval_cer": 0.1211970935121499, |
| "eval_loss": 0.10069698095321655, |
| "eval_runtime": 99.7318, |
| "eval_samples_per_second": 50.134, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.3372, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.000296247732299768, |
| "loss": 0.0804, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.000295463749823781, |
| "loss": 0.0766, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.0002946066890935644, |
| "loss": 0.0733, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.0002936769806803222, |
| "loss": 0.0707, |
| "step": 14000 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00029267509165208945, |
| "loss": 0.0661, |
| "step": 15000 |
| }, |
| { |
| "epoch": 1.06, |
| "eval_cer": 0.11274499234567369, |
| "eval_loss": 0.08334551751613617, |
| "eval_runtime": 99.5349, |
| "eval_samples_per_second": 50.234, |
| "eval_steps_per_second": 0.402, |
| "eval_wer": 0.3146, |
| "step": 15000 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00029160152533908566, |
| "loss": 0.0642, |
| "step": 16000 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.0002904568210808509, |
| "loss": 0.0624, |
| "step": 17000 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00028924155395529237, |
| "loss": 0.061, |
| "step": 18000 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00028795633448977547, |
| "loss": 0.0593, |
| "step": 19000 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.0002866018083544069, |
| "loss": 0.0585, |
| "step": 20000 |
| }, |
| { |
| "epoch": 1.42, |
| "eval_cer": 0.10940296254770478, |
| "eval_loss": 0.07396863400936127, |
| "eval_runtime": 99.5625, |
| "eval_samples_per_second": 50.22, |
| "eval_steps_per_second": 0.402, |
| "eval_wer": 0.3024, |
| "step": 20000 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.0002851786560376614, |
| "loss": 0.0568, |
| "step": 21000 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00028368759250451786, |
| "loss": 0.0552, |
| "step": 22000 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00028212936683727404, |
| "loss": 0.0542, |
| "step": 23000 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.0002805047618592216, |
| "loss": 0.0532, |
| "step": 24000 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.0002788145937413704, |
| "loss": 0.0526, |
| "step": 25000 |
| }, |
| { |
| "epoch": 1.77, |
| "eval_cer": 0.10444382155717027, |
| "eval_loss": 0.06628572195768356, |
| "eval_runtime": 99.5351, |
| "eval_samples_per_second": 50.234, |
| "eval_steps_per_second": 0.402, |
| "eval_wer": 0.293, |
| "step": 25000 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.00027705971159241994, |
| "loss": 0.0515, |
| "step": 26000 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.0002752409970321824, |
| "loss": 0.0505, |
| "step": 27000 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 0.000273359363748674, |
| "loss": 0.0501, |
| "step": 28000 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 0.0002714157570390952, |
| "loss": 0.0471, |
| "step": 29000 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 0.0002694111533349308, |
| "loss": 0.0459, |
| "step": 30000 |
| }, |
| { |
| "epoch": 2.13, |
| "eval_cer": 0.10159770585825481, |
| "eval_loss": 0.06294897198677063, |
| "eval_runtime": 99.7848, |
| "eval_samples_per_second": 50.108, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2848, |
| "step": 30000 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 0.00026734655971140956, |
| "loss": 0.0455, |
| "step": 31000 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 0.00026522301338156835, |
| "loss": 0.045, |
| "step": 32000 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 0.00026304158117517563, |
| "loss": 0.0448, |
| "step": 33000 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 0.0002608033590027766, |
| "loss": 0.0441, |
| "step": 34000 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 0.000258509471305128, |
| "loss": 0.0436, |
| "step": 35000 |
| }, |
| { |
| "epoch": 2.48, |
| "eval_cer": 0.10114491472433644, |
| "eval_loss": 0.06108950078487396, |
| "eval_runtime": 99.5917, |
| "eval_samples_per_second": 50.205, |
| "eval_steps_per_second": 0.402, |
| "eval_wer": 0.2796, |
| "step": 35000 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 0.00025616107048830045, |
| "loss": 0.0431, |
| "step": 36000 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 0.0002537593363447311, |
| "loss": 0.043, |
| "step": 37000 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 0.0002513054754605181, |
| "loss": 0.0427, |
| "step": 38000 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 0.0002488007206092547, |
| "loss": 0.0418, |
| "step": 39000 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 0.00024624633013270664, |
| "loss": 0.0417, |
| "step": 40000 |
| }, |
| { |
| "epoch": 2.83, |
| "eval_cer": 0.09972185687487872, |
| "eval_loss": 0.05735113471746445, |
| "eval_runtime": 99.9084, |
| "eval_samples_per_second": 50.046, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2768, |
| "step": 40000 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 0.0002436435873086449, |
| "loss": 0.0411, |
| "step": 41000 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 0.00024099379970615137, |
| "loss": 0.0406, |
| "step": 42000 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 0.00023829829852872037, |
| "loss": 0.0386, |
| "step": 43000 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 0.00023555843794548724, |
| "loss": 0.0375, |
| "step": 44000 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 0.00023277559441091917, |
| "loss": 0.0376, |
| "step": 45000 |
| }, |
| { |
| "epoch": 3.19, |
| "eval_cer": 0.09982966428771642, |
| "eval_loss": 0.05706231668591499, |
| "eval_runtime": 100.0238, |
| "eval_samples_per_second": 49.988, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2766, |
| "step": 45000 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 0.0002299511659733103, |
| "loss": 0.0373, |
| "step": 46000 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 0.0002270865715724285, |
| "loss": 0.0371, |
| "step": 47000 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 0.0002241832503266669, |
| "loss": 0.0368, |
| "step": 48000 |
| }, |
| { |
| "epoch": 3.47, |
| "learning_rate": 0.00022124266081005755, |
| "loss": 0.0366, |
| "step": 49000 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 0.0002182662803195115, |
| "loss": 0.0364, |
| "step": 50000 |
| }, |
| { |
| "epoch": 3.54, |
| "eval_cer": 0.09832036050798854, |
| "eval_loss": 0.05559751018881798, |
| "eval_runtime": 100.1039, |
| "eval_samples_per_second": 49.948, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2714, |
| "step": 50000 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 0.00021525560413265246, |
| "loss": 0.0363, |
| "step": 51000 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 0.00021221214475661745, |
| "loss": 0.0358, |
| "step": 52000 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 0.00020913743116820165, |
| "loss": 0.0358, |
| "step": 53000 |
| }, |
| { |
| "epoch": 3.83, |
| "learning_rate": 0.00020603300804572917, |
| "loss": 0.0356, |
| "step": 54000 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 0.00020290043499303573, |
| "loss": 0.0353, |
| "step": 55000 |
| }, |
| { |
| "epoch": 3.9, |
| "eval_cer": 0.09775976196123246, |
| "eval_loss": 0.053284887224435806, |
| "eval_runtime": 99.9875, |
| "eval_samples_per_second": 50.006, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2718, |
| "step": 55000 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 0.00019974128575595291, |
| "loss": 0.0349, |
| "step": 56000 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 0.000196557147431688, |
| "loss": 0.0335, |
| "step": 57000 |
| }, |
| { |
| "epoch": 4.11, |
| "learning_rate": 0.00019334961967149597, |
| "loss": 0.0324, |
| "step": 58000 |
| }, |
| { |
| "epoch": 4.18, |
| "learning_rate": 0.00019012031387704483, |
| "loss": 0.0323, |
| "step": 59000 |
| }, |
| { |
| "epoch": 4.25, |
| "learning_rate": 0.00018687085239087786, |
| "loss": 0.0323, |
| "step": 60000 |
| }, |
| { |
| "epoch": 4.25, |
| "eval_cer": 0.0979969382694754, |
| "eval_loss": 0.05237960070371628, |
| "eval_runtime": 99.6271, |
| "eval_samples_per_second": 50.187, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2696, |
| "step": 60000 |
| }, |
| { |
| "epoch": 4.32, |
| "learning_rate": 0.00018360286768137894, |
| "loss": 0.0322, |
| "step": 61000 |
| }, |
| { |
| "epoch": 4.39, |
| "learning_rate": 0.00018031800152265137, |
| "loss": 0.032, |
| "step": 62000 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 0.00017701790416972107, |
| "loss": 0.0319, |
| "step": 63000 |
| }, |
| { |
| "epoch": 4.53, |
| "learning_rate": 0.00017370423352948002, |
| "loss": 0.0318, |
| "step": 64000 |
| }, |
| { |
| "epoch": 4.6, |
| "learning_rate": 0.00017037865432778442, |
| "loss": 0.0316, |
| "step": 65000 |
| }, |
| { |
| "epoch": 4.6, |
| "eval_cer": 0.09584079001272128, |
| "eval_loss": 0.052747271955013275, |
| "eval_runtime": 99.8825, |
| "eval_samples_per_second": 50.059, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2678, |
| "step": 65000 |
| }, |
| { |
| "epoch": 4.68, |
| "learning_rate": 0.00016704283727312792, |
| "loss": 0.0315, |
| "step": 66000 |
| }, |
| { |
| "epoch": 4.75, |
| "learning_rate": 0.00016369845821730933, |
| "loss": 0.0314, |
| "step": 67000 |
| }, |
| { |
| "epoch": 4.82, |
| "learning_rate": 0.00016034719731351576, |
| "loss": 0.0314, |
| "step": 68000 |
| }, |
| { |
| "epoch": 4.89, |
| "learning_rate": 0.00015699073817224542, |
| "loss": 0.0312, |
| "step": 69000 |
| }, |
| { |
| "epoch": 4.96, |
| "learning_rate": 0.00015363076701549341, |
| "loss": 0.031, |
| "step": 70000 |
| }, |
| { |
| "epoch": 4.96, |
| "eval_cer": 0.09558205222191078, |
| "eval_loss": 0.05028079077601433, |
| "eval_runtime": 99.8117, |
| "eval_samples_per_second": 50.094, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2664, |
| "step": 70000 |
| }, |
| { |
| "epoch": 5.03, |
| "learning_rate": 0.00015026897182962535, |
| "loss": 0.0303, |
| "step": 71000 |
| }, |
| { |
| "epoch": 5.1, |
| "learning_rate": 0.00014690704151736484, |
| "loss": 0.0286, |
| "step": 72000 |
| }, |
| { |
| "epoch": 5.17, |
| "learning_rate": 0.0001435466650493204, |
| "loss": 0.0287, |
| "step": 73000 |
| }, |
| { |
| "epoch": 5.24, |
| "learning_rate": 0.0001401895306154785, |
| "loss": 0.0284, |
| "step": 74000 |
| }, |
| { |
| "epoch": 5.31, |
| "learning_rate": 0.0001368373247770885, |
| "loss": 0.0287, |
| "step": 75000 |
| }, |
| { |
| "epoch": 5.31, |
| "eval_cer": 0.09566829815218095, |
| "eval_loss": 0.04991844296455383, |
| "eval_runtime": 99.6863, |
| "eval_samples_per_second": 50.157, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2642, |
| "step": 75000 |
| }, |
| { |
| "epoch": 5.38, |
| "learning_rate": 0.00013349173161936601, |
| "loss": 0.0287, |
| "step": 76000 |
| }, |
| { |
| "epoch": 5.45, |
| "learning_rate": 0.00013015443190544018, |
| "loss": 0.0283, |
| "step": 77000 |
| }, |
| { |
| "epoch": 5.53, |
| "learning_rate": 0.00012682710223196978, |
| "loss": 0.0284, |
| "step": 78000 |
| }, |
| { |
| "epoch": 5.6, |
| "learning_rate": 0.00012351141418685273, |
| "loss": 0.0286, |
| "step": 79000 |
| }, |
| { |
| "epoch": 5.67, |
| "learning_rate": 0.00012020903350945151, |
| "loss": 0.0282, |
| "step": 80000 |
| }, |
| { |
| "epoch": 5.67, |
| "eval_cer": 0.09588391297785635, |
| "eval_loss": 0.04885885864496231, |
| "eval_runtime": 99.7588, |
| "eval_samples_per_second": 50.121, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.264, |
| "step": 80000 |
| }, |
| { |
| "epoch": 5.74, |
| "learning_rate": 0.00011692161925375738, |
| "loss": 0.0282, |
| "step": 81000 |
| }, |
| { |
| "epoch": 5.81, |
| "learning_rate": 0.00011365082295491233, |
| "loss": 0.0279, |
| "step": 82000 |
| }, |
| { |
| "epoch": 5.88, |
| "learning_rate": 0.00011039828779950928, |
| "loss": 0.0281, |
| "step": 83000 |
| }, |
| { |
| "epoch": 5.95, |
| "learning_rate": 0.0001071656478000858, |
| "loss": 0.028, |
| "step": 84000 |
| }, |
| { |
| "epoch": 6.02, |
| "learning_rate": 0.00010395452697422703, |
| "loss": 0.0275, |
| "step": 85000 |
| }, |
| { |
| "epoch": 6.02, |
| "eval_cer": 0.0948058388494793, |
| "eval_loss": 0.048800304532051086, |
| "eval_runtime": 99.8744, |
| "eval_samples_per_second": 50.063, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2616, |
| "step": 85000 |
| }, |
| { |
| "epoch": 6.09, |
| "learning_rate": 0.00010076653852868962, |
| "loss": 0.026, |
| "step": 86000 |
| }, |
| { |
| "epoch": 6.16, |
| "learning_rate": 9.760328404895728e-05, |
| "loss": 0.0258, |
| "step": 87000 |
| }, |
| { |
| "epoch": 6.23, |
| "learning_rate": 9.446635269463389e-05, |
| "loss": 0.0258, |
| "step": 88000 |
| }, |
| { |
| "epoch": 6.3, |
| "learning_rate": 9.135732040107998e-05, |
| "loss": 0.026, |
| "step": 89000 |
| }, |
| { |
| "epoch": 6.38, |
| "learning_rate": 8.82777490876921e-05, |
| "loss": 0.0259, |
| "step": 90000 |
| }, |
| { |
| "epoch": 6.38, |
| "eval_cer": 0.09374932620366977, |
| "eval_loss": 0.0478358194231987, |
| "eval_runtime": 99.8791, |
| "eval_samples_per_second": 50.061, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2608, |
| "step": 90000 |
| }, |
| { |
| "epoch": 6.45, |
| "learning_rate": 8.522918587322418e-05, |
| "loss": 0.0259, |
| "step": 91000 |
| }, |
| { |
| "epoch": 6.52, |
| "learning_rate": 8.22131622985438e-05, |
| "loss": 0.026, |
| "step": 92000 |
| }, |
| { |
| "epoch": 6.59, |
| "learning_rate": 7.923119355721526e-05, |
| "loss": 0.0259, |
| "step": 93000 |
| }, |
| { |
| "epoch": 6.66, |
| "learning_rate": 7.628477773429438e-05, |
| "loss": 0.0257, |
| "step": 94000 |
| }, |
| { |
| "epoch": 6.73, |
| "learning_rate": 7.3375395053719e-05, |
| "loss": 0.0257, |
| "step": 95000 |
| }, |
| { |
| "epoch": 6.73, |
| "eval_cer": 0.09379244916880485, |
| "eval_loss": 0.04708043858408928, |
| "eval_runtime": 99.9161, |
| "eval_samples_per_second": 50.042, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.259, |
| "step": 95000 |
| }, |
| { |
| "epoch": 6.8, |
| "learning_rate": 7.050450713467216e-05, |
| "loss": 0.0255, |
| "step": 96000 |
| }, |
| { |
| "epoch": 6.87, |
| "learning_rate": 6.767355625729215e-05, |
| "loss": 0.0255, |
| "step": 97000 |
| }, |
| { |
| "epoch": 6.94, |
| "learning_rate": 6.488396463809805e-05, |
| "loss": 0.0255, |
| "step": 98000 |
| }, |
| { |
| "epoch": 7.01, |
| "learning_rate": 6.213713371549497e-05, |
| "loss": 0.025, |
| "step": 99000 |
| }, |
| { |
| "epoch": 7.08, |
| "learning_rate": 5.943444344571755e-05, |
| "loss": 0.0238, |
| "step": 100000 |
| }, |
| { |
| "epoch": 7.08, |
| "eval_cer": 0.0940296254770478, |
| "eval_loss": 0.047569289803504944, |
| "eval_runtime": 99.6286, |
| "eval_samples_per_second": 50.186, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2586, |
| "step": 100000 |
| }, |
| { |
| "epoch": 7.15, |
| "learning_rate": 5.6777251609566e-05, |
| "loss": 0.0242, |
| "step": 101000 |
| }, |
| { |
| "epoch": 7.23, |
| "learning_rate": 5.416689313028253e-05, |
| "loss": 0.0239, |
| "step": 102000 |
| }, |
| { |
| "epoch": 7.3, |
| "learning_rate": 5.1604679402911015e-05, |
| "loss": 0.024, |
| "step": 103000 |
| }, |
| { |
| "epoch": 7.37, |
| "learning_rate": 4.9091897635476726e-05, |
| "loss": 0.0242, |
| "step": 104000 |
| }, |
| { |
| "epoch": 7.44, |
| "learning_rate": 4.6629810202317166e-05, |
| "loss": 0.0239, |
| "step": 105000 |
| }, |
| { |
| "epoch": 7.44, |
| "eval_cer": 0.09372776472110222, |
| "eval_loss": 0.04707524552941322, |
| "eval_runtime": 99.582, |
| "eval_samples_per_second": 50.21, |
| "eval_steps_per_second": 0.402, |
| "eval_wer": 0.2576, |
| "step": 105000 |
| }, |
| { |
| "epoch": 7.51, |
| "learning_rate": 4.421965400988918e-05, |
| "loss": 0.0239, |
| "step": 106000 |
| }, |
| { |
| "epoch": 7.58, |
| "learning_rate": 4.1862639875370016e-05, |
| "loss": 0.024, |
| "step": 107000 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 3.955995191836581e-05, |
| "loss": 0.0238, |
| "step": 108000 |
| }, |
| { |
| "epoch": 7.72, |
| "learning_rate": 3.731274696603201e-05, |
| "loss": 0.0239, |
| "step": 109000 |
| }, |
| { |
| "epoch": 7.79, |
| "learning_rate": 3.512215397190527e-05, |
| "loss": 0.0237, |
| "step": 110000 |
| }, |
| { |
| "epoch": 7.79, |
| "eval_cer": 0.09361995730826451, |
| "eval_loss": 0.046346429735422134, |
| "eval_runtime": 99.9122, |
| "eval_samples_per_second": 50.044, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2564, |
| "step": 110000 |
| }, |
| { |
| "epoch": 7.86, |
| "learning_rate": 3.298927344873821e-05, |
| "loss": 0.0237, |
| "step": 111000 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 3.091517691562284e-05, |
| "loss": 0.0237, |
| "step": 112000 |
| }, |
| { |
| "epoch": 8.01, |
| "learning_rate": 2.890090635967912e-05, |
| "loss": 0.024, |
| "step": 113000 |
| }, |
| { |
| "epoch": 8.08, |
| "learning_rate": 2.694747371258042e-05, |
| "loss": 0.0227, |
| "step": 114000 |
| }, |
| { |
| "epoch": 8.15, |
| "learning_rate": 2.505586034217802e-05, |
| "loss": 0.0226, |
| "step": 115000 |
| }, |
| { |
| "epoch": 8.15, |
| "eval_cer": 0.0940296254770478, |
| "eval_loss": 0.0467340350151062, |
| "eval_runtime": 100.0479, |
| "eval_samples_per_second": 49.976, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2582, |
| "step": 115000 |
| }, |
| { |
| "epoch": 8.22, |
| "learning_rate": 2.3227016559480356e-05, |
| "loss": 0.0228, |
| "step": 116000 |
| }, |
| { |
| "epoch": 8.29, |
| "learning_rate": 2.1461861141234628e-05, |
| "loss": 0.0226, |
| "step": 117000 |
| }, |
| { |
| "epoch": 8.36, |
| "learning_rate": 1.9761280868350654e-05, |
| "loss": 0.0228, |
| "step": 118000 |
| }, |
| { |
| "epoch": 8.43, |
| "learning_rate": 1.8126130080398725e-05, |
| "loss": 0.0226, |
| "step": 119000 |
| }, |
| { |
| "epoch": 8.5, |
| "learning_rate": 1.655723024640553e-05, |
| "loss": 0.0228, |
| "step": 120000 |
| }, |
| { |
| "epoch": 8.5, |
| "eval_cer": 0.09323185062204878, |
| "eval_loss": 0.04636606574058533, |
| "eval_runtime": 99.8629, |
| "eval_samples_per_second": 50.069, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.255, |
| "step": 120000 |
| }, |
| { |
| "epoch": 8.57, |
| "learning_rate": 1.5055369552163509e-05, |
| "loss": 0.0228, |
| "step": 121000 |
| }, |
| { |
| "epoch": 8.64, |
| "learning_rate": 1.3621302504261194e-05, |
| "loss": 0.0229, |
| "step": 122000 |
| }, |
| { |
| "epoch": 8.71, |
| "learning_rate": 1.2255749551033205e-05, |
| "loss": 0.0227, |
| "step": 123000 |
| }, |
| { |
| "epoch": 8.78, |
| "learning_rate": 1.0959396720620555e-05, |
| "loss": 0.0226, |
| "step": 124000 |
| }, |
| { |
| "epoch": 8.86, |
| "learning_rate": 9.732895276323099e-06, |
| "loss": 0.0227, |
| "step": 125000 |
| }, |
| { |
| "epoch": 8.86, |
| "eval_cer": 0.0935552728605619, |
| "eval_loss": 0.04629843682050705, |
| "eval_runtime": 100.0662, |
| "eval_samples_per_second": 49.967, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2578, |
| "step": 125000 |
| }, |
| { |
| "epoch": 8.93, |
| "learning_rate": 8.576861389416939e-06, |
| "loss": 0.0227, |
| "step": 126000 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 7.4918758296016734e-06, |
| "loss": 0.0227, |
| "step": 127000 |
| }, |
| { |
| "epoch": 9.07, |
| "learning_rate": 6.478483673232537e-06, |
| "loss": 0.0223, |
| "step": 128000 |
| }, |
| { |
| "epoch": 9.14, |
| "learning_rate": 5.537194029484349e-06, |
| "loss": 0.0222, |
| "step": 129000 |
| }, |
| { |
| "epoch": 9.21, |
| "learning_rate": 4.668479784584583e-06, |
| "loss": 0.0221, |
| "step": 130000 |
| }, |
| { |
| "epoch": 9.21, |
| "eval_cer": 0.09361995730826451, |
| "eval_loss": 0.04640863090753555, |
| "eval_runtime": 99.7393, |
| "eval_samples_per_second": 50.131, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2562, |
| "step": 130000 |
| }, |
| { |
| "epoch": 9.28, |
| "learning_rate": 3.872777364244245e-06, |
| "loss": 0.0223, |
| "step": 131000 |
| }, |
| { |
| "epoch": 9.35, |
| "learning_rate": 3.150486514405798e-06, |
| "loss": 0.0222, |
| "step": 132000 |
| }, |
| { |
| "epoch": 9.42, |
| "learning_rate": 2.50197010041826e-06, |
| "loss": 0.022, |
| "step": 133000 |
| }, |
| { |
| "epoch": 9.49, |
| "learning_rate": 1.9275539247405437e-06, |
| "loss": 0.0222, |
| "step": 134000 |
| }, |
| { |
| "epoch": 9.56, |
| "learning_rate": 1.4275265632643806e-06, |
| "loss": 0.0223, |
| "step": 135000 |
| }, |
| { |
| "epoch": 9.56, |
| "eval_cer": 0.09357683434312944, |
| "eval_loss": 0.046345390379428864, |
| "eval_runtime": 99.9431, |
| "eval_samples_per_second": 50.028, |
| "eval_steps_per_second": 0.4, |
| "eval_wer": 0.2564, |
| "step": 135000 |
| }, |
| { |
| "epoch": 9.63, |
| "learning_rate": 1.0021392203391932e-06, |
| "loss": 0.022, |
| "step": 136000 |
| }, |
| { |
| "epoch": 9.71, |
| "learning_rate": 6.516056025718585e-07, |
| "loss": 0.0221, |
| "step": 137000 |
| }, |
| { |
| "epoch": 9.78, |
| "learning_rate": 3.76101811464391e-07, |
| "loss": 0.0223, |
| "step": 138000 |
| }, |
| { |
| "epoch": 9.85, |
| "learning_rate": 1.7576625494392648e-07, |
| "loss": 0.0221, |
| "step": 139000 |
| }, |
| { |
| "epoch": 9.92, |
| "learning_rate": 5.0699577829210744e-08, |
| "loss": 0.0223, |
| "step": 140000 |
| }, |
| { |
| "epoch": 9.92, |
| "eval_cer": 0.0937708876862373, |
| "eval_loss": 0.046362996101379395, |
| "eval_runtime": 99.8262, |
| "eval_samples_per_second": 50.087, |
| "eval_steps_per_second": 0.401, |
| "eval_wer": 0.2566, |
| "step": 140000 |
| } |
| ], |
| "max_steps": 141160, |
| "num_train_epochs": 10, |
| "total_flos": 4.3451206845736243e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
