| { | |
| "best_metric": 0.3207731246948242, | |
| "best_model_checkpoint": "./Hubert-common_voice-phonemes-debug/checkpoint-4500", | |
| "epoch": 30.0, | |
| "eval_steps": 100, | |
| "global_step": 11280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26595744680851063, | |
| "eval_cer": 1.829171076931253, | |
| "eval_loss": 18.536373138427734, | |
| "eval_runtime": 213.5728, | |
| "eval_samples_per_second": 23.219, | |
| "eval_steps_per_second": 2.903, | |
| "eval_wer": 1.0645295587010823, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "eval_cer": 0.9812975256754901, | |
| "eval_loss": 8.279097557067871, | |
| "eval_runtime": 218.6029, | |
| "eval_samples_per_second": 22.685, | |
| "eval_steps_per_second": 2.836, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7978723404255319, | |
| "eval_cer": 0.9813063831106427, | |
| "eval_loss": 7.022369384765625, | |
| "eval_runtime": 215.2791, | |
| "eval_samples_per_second": 23.035, | |
| "eval_steps_per_second": 2.88, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_cer": 0.9813019543930664, | |
| "eval_loss": 6.310593128204346, | |
| "eval_runtime": 219.0435, | |
| "eval_samples_per_second": 22.639, | |
| "eval_steps_per_second": 2.83, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "grad_norm": 28.102890014648438, | |
| "learning_rate": 1.1903999999999998e-05, | |
| "loss": 8.9892, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "eval_cer": 0.9813063831106427, | |
| "eval_loss": 5.522346496582031, | |
| "eval_runtime": 213.327, | |
| "eval_samples_per_second": 23.246, | |
| "eval_steps_per_second": 2.906, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "eval_cer": 0.9813108118282189, | |
| "eval_loss": 4.712064266204834, | |
| "eval_runtime": 215.4766, | |
| "eval_samples_per_second": 23.014, | |
| "eval_steps_per_second": 2.877, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8617021276595744, | |
| "eval_cer": 0.9812975256754901, | |
| "eval_loss": 4.002798080444336, | |
| "eval_runtime": 215.7516, | |
| "eval_samples_per_second": 22.985, | |
| "eval_steps_per_second": 2.874, | |
| "eval_wer": 1.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "eval_cer": 0.9813108118282189, | |
| "eval_loss": 3.475456953048706, | |
| "eval_runtime": 214.2882, | |
| "eval_samples_per_second": 23.142, | |
| "eval_steps_per_second": 2.893, | |
| "eval_wer": 1.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.393617021276596, | |
| "eval_cer": 0.9813019543930664, | |
| "eval_loss": 3.1987791061401367, | |
| "eval_runtime": 216.1589, | |
| "eval_samples_per_second": 22.941, | |
| "eval_steps_per_second": 2.868, | |
| "eval_wer": 1.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 2.371589422225952, | |
| "learning_rate": 2.3903999999999997e-05, | |
| "loss": 3.7187, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "eval_cer": 0.9813108118282189, | |
| "eval_loss": 3.0792152881622314, | |
| "eval_runtime": 213.8516, | |
| "eval_samples_per_second": 23.189, | |
| "eval_steps_per_second": 2.899, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.925531914893617, | |
| "eval_cer": 0.9812930969579139, | |
| "eval_loss": 3.0459136962890625, | |
| "eval_runtime": 216.2299, | |
| "eval_samples_per_second": 22.934, | |
| "eval_steps_per_second": 2.867, | |
| "eval_wer": 1.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.1914893617021276, | |
| "eval_cer": 0.9813152405457951, | |
| "eval_loss": 3.035966396331787, | |
| "eval_runtime": 217.4243, | |
| "eval_samples_per_second": 22.808, | |
| "eval_steps_per_second": 2.852, | |
| "eval_wer": 1.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.4574468085106385, | |
| "eval_cer": 0.9813108118282189, | |
| "eval_loss": 3.008437395095825, | |
| "eval_runtime": 215.1294, | |
| "eval_samples_per_second": 23.051, | |
| "eval_steps_per_second": 2.882, | |
| "eval_wer": 1.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.723404255319149, | |
| "eval_cer": 0.9343265470617673, | |
| "eval_loss": 2.495579481124878, | |
| "eval_runtime": 217.105, | |
| "eval_samples_per_second": 22.841, | |
| "eval_steps_per_second": 2.856, | |
| "eval_wer": 1.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.9893617021276597, | |
| "grad_norm": 3.707914352416992, | |
| "learning_rate": 3.5903999999999994e-05, | |
| "loss": 2.783, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.9893617021276597, | |
| "eval_cer": 0.33314142223836246, | |
| "eval_loss": 1.4417579174041748, | |
| "eval_runtime": 217.5545, | |
| "eval_samples_per_second": 22.794, | |
| "eval_steps_per_second": 2.85, | |
| "eval_wer": 1.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "eval_cer": 0.27530679941009484, | |
| "eval_loss": 1.0227618217468262, | |
| "eval_runtime": 217.2546, | |
| "eval_samples_per_second": 22.826, | |
| "eval_steps_per_second": 2.854, | |
| "eval_wer": 1.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.5212765957446805, | |
| "eval_cer": 0.2531632115288376, | |
| "eval_loss": 0.8218135237693787, | |
| "eval_runtime": 219.2044, | |
| "eval_samples_per_second": 22.623, | |
| "eval_steps_per_second": 2.828, | |
| "eval_wer": 1.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.787234042553192, | |
| "eval_cer": 0.24330045748652562, | |
| "eval_loss": 0.7084201574325562, | |
| "eval_runtime": 216.8198, | |
| "eval_samples_per_second": 22.872, | |
| "eval_steps_per_second": 2.86, | |
| "eval_wer": 1.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.053191489361702, | |
| "eval_cer": 0.23373885623939875, | |
| "eval_loss": 0.6305696368217468, | |
| "eval_runtime": 218.0682, | |
| "eval_samples_per_second": 22.741, | |
| "eval_steps_per_second": 2.843, | |
| "eval_wer": 1.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.319148936170213, | |
| "grad_norm": 2.717346429824829, | |
| "learning_rate": 4.7903999999999994e-05, | |
| "loss": 0.8659, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.319148936170213, | |
| "eval_cer": 0.23099305134212286, | |
| "eval_loss": 0.5933591723442078, | |
| "eval_runtime": 218.7287, | |
| "eval_samples_per_second": 22.672, | |
| "eval_steps_per_second": 2.835, | |
| "eval_wer": 1.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.585106382978723, | |
| "eval_cer": 0.228406680277592, | |
| "eval_loss": 0.5647820234298706, | |
| "eval_runtime": 215.722, | |
| "eval_samples_per_second": 22.988, | |
| "eval_steps_per_second": 2.874, | |
| "eval_wer": 1.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.851063829787234, | |
| "eval_cer": 0.22140930650711474, | |
| "eval_loss": 0.5329573750495911, | |
| "eval_runtime": 218.357, | |
| "eval_samples_per_second": 22.711, | |
| "eval_steps_per_second": 2.839, | |
| "eval_wer": 1.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.117021276595745, | |
| "eval_cer": 0.22092214757372708, | |
| "eval_loss": 0.5139152407646179, | |
| "eval_runtime": 217.5924, | |
| "eval_samples_per_second": 22.79, | |
| "eval_steps_per_second": 2.849, | |
| "eval_wer": 1.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.382978723404255, | |
| "eval_cer": 0.21591769671256295, | |
| "eval_loss": 0.4906846582889557, | |
| "eval_runtime": 217.5534, | |
| "eval_samples_per_second": 22.794, | |
| "eval_steps_per_second": 2.85, | |
| "eval_wer": 1.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.648936170212766, | |
| "grad_norm": 6.231712341308594, | |
| "learning_rate": 5.9903999999999994e-05, | |
| "loss": 0.5271, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.648936170212766, | |
| "eval_cer": 0.2159929849113592, | |
| "eval_loss": 0.46404561400413513, | |
| "eval_runtime": 217.7416, | |
| "eval_samples_per_second": 22.775, | |
| "eval_steps_per_second": 2.847, | |
| "eval_wer": 1.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.914893617021277, | |
| "eval_cer": 0.21120111249385515, | |
| "eval_loss": 0.4608772397041321, | |
| "eval_runtime": 216.2932, | |
| "eval_samples_per_second": 22.927, | |
| "eval_steps_per_second": 2.866, | |
| "eval_wer": 1.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.180851063829787, | |
| "eval_cer": 0.2096732049300484, | |
| "eval_loss": 0.4550062417984009, | |
| "eval_runtime": 219.5448, | |
| "eval_samples_per_second": 22.588, | |
| "eval_steps_per_second": 2.824, | |
| "eval_wer": 1.0001387732445184, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.446808510638298, | |
| "eval_cer": 0.210000930030691, | |
| "eval_loss": 0.4601040184497833, | |
| "eval_runtime": 218.3231, | |
| "eval_samples_per_second": 22.714, | |
| "eval_steps_per_second": 2.84, | |
| "eval_wer": 0.9991673605328892, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.712765957446808, | |
| "eval_cer": 0.20508948223862816, | |
| "eval_loss": 0.4290345013141632, | |
| "eval_runtime": 218.312, | |
| "eval_samples_per_second": 22.715, | |
| "eval_steps_per_second": 2.84, | |
| "eval_wer": 0.9952817096863724, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 7.9787234042553195, | |
| "grad_norm": 2.573235273361206, | |
| "learning_rate": 7.1904e-05, | |
| "loss": 0.4244, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.9787234042553195, | |
| "eval_cer": 0.20240125066984355, | |
| "eval_loss": 0.42562517523765564, | |
| "eval_runtime": 219.9498, | |
| "eval_samples_per_second": 22.546, | |
| "eval_steps_per_second": 2.819, | |
| "eval_wer": 0.9970857618651124, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.24468085106383, | |
| "eval_cer": 0.2014180753679157, | |
| "eval_loss": 0.4134505093097687, | |
| "eval_runtime": 218.0911, | |
| "eval_samples_per_second": 22.738, | |
| "eval_steps_per_second": 2.843, | |
| "eval_wer": 0.9998612267554815, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "eval_cer": 0.1998945965216852, | |
| "eval_loss": 0.41247421503067017, | |
| "eval_runtime": 220.4438, | |
| "eval_samples_per_second": 22.496, | |
| "eval_steps_per_second": 2.813, | |
| "eval_wer": 0.9955592561754094, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.77659574468085, | |
| "eval_cer": 0.1926979304602766, | |
| "eval_loss": 0.3886178731918335, | |
| "eval_runtime": 219.8802, | |
| "eval_samples_per_second": 22.553, | |
| "eval_steps_per_second": 2.82, | |
| "eval_wer": 0.9941715237302248, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 9.042553191489361, | |
| "eval_cer": 0.1911124495679786, | |
| "eval_loss": 0.38326719403266907, | |
| "eval_runtime": 219.6869, | |
| "eval_samples_per_second": 22.573, | |
| "eval_steps_per_second": 2.822, | |
| "eval_wer": 1.0005550929780738, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 9.308510638297872, | |
| "grad_norm": 2.091050148010254, | |
| "learning_rate": 8.390399999999999e-05, | |
| "loss": 0.3373, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.308510638297872, | |
| "eval_cer": 0.1886855123361928, | |
| "eval_loss": 0.36107370257377625, | |
| "eval_runtime": 222.4868, | |
| "eval_samples_per_second": 22.289, | |
| "eval_steps_per_second": 2.787, | |
| "eval_wer": 1.0363585900638357, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.574468085106384, | |
| "eval_cer": 0.18428336706539888, | |
| "eval_loss": 0.3584689497947693, | |
| "eval_runtime": 217.5818, | |
| "eval_samples_per_second": 22.791, | |
| "eval_steps_per_second": 2.85, | |
| "eval_wer": 1.0080488481820704, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.840425531914894, | |
| "eval_cer": 0.18549683568129177, | |
| "eval_loss": 0.3562237024307251, | |
| "eval_runtime": 221.8447, | |
| "eval_samples_per_second": 22.353, | |
| "eval_steps_per_second": 2.795, | |
| "eval_wer": 0.9980571745767416, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 10.106382978723405, | |
| "eval_cer": 0.1799387951230962, | |
| "eval_loss": 0.3412463068962097, | |
| "eval_runtime": 217.8756, | |
| "eval_samples_per_second": 22.761, | |
| "eval_steps_per_second": 2.846, | |
| "eval_wer": 0.9883430474604497, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 10.372340425531915, | |
| "eval_cer": 0.18462437831877024, | |
| "eval_loss": 0.35612642765045166, | |
| "eval_runtime": 218.9988, | |
| "eval_samples_per_second": 22.644, | |
| "eval_steps_per_second": 2.831, | |
| "eval_wer": 0.9834859839023037, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 10.638297872340425, | |
| "grad_norm": 2.690404176712036, | |
| "learning_rate": 9.5904e-05, | |
| "loss": 0.2779, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.638297872340425, | |
| "eval_cer": 0.17977050385519866, | |
| "eval_loss": 0.34815147519111633, | |
| "eval_runtime": 221.1151, | |
| "eval_samples_per_second": 22.427, | |
| "eval_steps_per_second": 2.804, | |
| "eval_wer": 0.9772411878989731, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.904255319148936, | |
| "eval_cer": 0.17927891620423475, | |
| "eval_loss": 0.3266104757785797, | |
| "eval_runtime": 217.4603, | |
| "eval_samples_per_second": 22.804, | |
| "eval_steps_per_second": 2.851, | |
| "eval_wer": 0.9794615598112684, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 11.170212765957446, | |
| "eval_cer": 0.17892019008055837, | |
| "eval_loss": 0.34835320711135864, | |
| "eval_runtime": 220.4292, | |
| "eval_samples_per_second": 22.497, | |
| "eval_steps_per_second": 2.813, | |
| "eval_wer": 0.9791840133222315, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 11.436170212765958, | |
| "eval_cer": 0.17989007922975744, | |
| "eval_loss": 0.33775731921195984, | |
| "eval_runtime": 218.1639, | |
| "eval_samples_per_second": 22.731, | |
| "eval_steps_per_second": 2.842, | |
| "eval_wer": 0.9991673605328892, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 11.702127659574469, | |
| "eval_cer": 0.17952249567092857, | |
| "eval_loss": 0.33295243978500366, | |
| "eval_runtime": 218.1937, | |
| "eval_samples_per_second": 22.728, | |
| "eval_steps_per_second": 2.842, | |
| "eval_wer": 0.9764085484318623, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 11.96808510638298, | |
| "grad_norm": 2.2231483459472656, | |
| "learning_rate": 0.00010790399999999999, | |
| "loss": 0.2409, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 11.96808510638298, | |
| "eval_cer": 0.17923020031089598, | |
| "eval_loss": 0.3207731246948242, | |
| "eval_runtime": 218.6698, | |
| "eval_samples_per_second": 22.678, | |
| "eval_steps_per_second": 2.835, | |
| "eval_wer": 0.9780738273660838, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.23404255319149, | |
| "eval_cer": 0.18048352738497514, | |
| "eval_loss": 0.3602401614189148, | |
| "eval_runtime": 217.2746, | |
| "eval_samples_per_second": 22.824, | |
| "eval_steps_per_second": 2.854, | |
| "eval_wer": 0.97571468220927, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_cer": 0.17876961368296582, | |
| "eval_loss": 0.3362875282764435, | |
| "eval_runtime": 219.2626, | |
| "eval_samples_per_second": 22.617, | |
| "eval_steps_per_second": 2.828, | |
| "eval_wer": 0.9938939772411879, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 12.76595744680851, | |
| "eval_cer": 0.17953135310608107, | |
| "eval_loss": 0.32531023025512695, | |
| "eval_runtime": 217.8058, | |
| "eval_samples_per_second": 22.768, | |
| "eval_steps_per_second": 2.847, | |
| "eval_wer": 0.9732167638079379, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 13.03191489361702, | |
| "eval_cer": 0.17615224159540122, | |
| "eval_loss": 0.3284818232059479, | |
| "eval_runtime": 218.6415, | |
| "eval_samples_per_second": 22.681, | |
| "eval_steps_per_second": 2.836, | |
| "eval_wer": 0.971135165140161, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 13.297872340425531, | |
| "grad_norm": 2.2732036113739014, | |
| "learning_rate": 0.00011990399999999998, | |
| "loss": 0.2104, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.297872340425531, | |
| "eval_cer": 0.17691398101851646, | |
| "eval_loss": 0.32327184081077576, | |
| "eval_runtime": 218.7534, | |
| "eval_samples_per_second": 22.669, | |
| "eval_steps_per_second": 2.834, | |
| "eval_wer": 0.9729392173189009, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.563829787234042, | |
| "eval_cer": 0.18268017130279585, | |
| "eval_loss": 0.3362744450569153, | |
| "eval_runtime": 216.3239, | |
| "eval_samples_per_second": 22.924, | |
| "eval_steps_per_second": 2.866, | |
| "eval_wer": 0.97751873438801, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 13.829787234042554, | |
| "eval_cer": 0.17587766110567363, | |
| "eval_loss": 0.33709821105003357, | |
| "eval_runtime": 219.8171, | |
| "eval_samples_per_second": 22.56, | |
| "eval_steps_per_second": 2.821, | |
| "eval_wer": 0.9683597002497918, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 14.095744680851064, | |
| "eval_cer": 0.17777315222830925, | |
| "eval_loss": 0.3463989496231079, | |
| "eval_runtime": 216.1817, | |
| "eval_samples_per_second": 22.939, | |
| "eval_steps_per_second": 2.868, | |
| "eval_wer": 0.9730779905634194, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 14.361702127659575, | |
| "eval_cer": 0.17830459833745943, | |
| "eval_loss": 0.3450472950935364, | |
| "eval_runtime": 217.8272, | |
| "eval_samples_per_second": 22.766, | |
| "eval_steps_per_second": 2.846, | |
| "eval_wer": 0.9776575076325285, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 14.627659574468085, | |
| "grad_norm": 3.842231273651123, | |
| "learning_rate": 0.000131904, | |
| "loss": 0.1947, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.627659574468085, | |
| "eval_cer": 0.1773037081652266, | |
| "eval_loss": 0.3442366421222687, | |
| "eval_runtime": 219.014, | |
| "eval_samples_per_second": 22.642, | |
| "eval_steps_per_second": 2.831, | |
| "eval_wer": 0.9680821537607549, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.893617021276595, | |
| "eval_cer": 0.17800344554227432, | |
| "eval_loss": 0.3346150517463684, | |
| "eval_runtime": 216.342, | |
| "eval_samples_per_second": 22.922, | |
| "eval_steps_per_second": 2.866, | |
| "eval_wer": 0.9858451290591174, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 15.159574468085106, | |
| "eval_cer": 0.17705569998095652, | |
| "eval_loss": 0.35239535570144653, | |
| "eval_runtime": 219.7446, | |
| "eval_samples_per_second": 22.567, | |
| "eval_steps_per_second": 2.821, | |
| "eval_wer": 0.9732167638079379, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 15.425531914893616, | |
| "eval_cer": 0.17744542712766664, | |
| "eval_loss": 0.3413674235343933, | |
| "eval_runtime": 216.7948, | |
| "eval_samples_per_second": 22.874, | |
| "eval_steps_per_second": 2.86, | |
| "eval_wer": 0.9782126006106022, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 15.691489361702128, | |
| "eval_cer": 0.1765641123299926, | |
| "eval_loss": 0.3437710702419281, | |
| "eval_runtime": 217.8111, | |
| "eval_samples_per_second": 22.767, | |
| "eval_steps_per_second": 2.847, | |
| "eval_wer": 1.0019428254232583, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 15.957446808510639, | |
| "grad_norm": 1.6587754487991333, | |
| "learning_rate": 0.00014390399999999998, | |
| "loss": 0.1892, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 15.957446808510639, | |
| "eval_cer": 0.18023551920070505, | |
| "eval_loss": 0.3391115367412567, | |
| "eval_runtime": 220.8887, | |
| "eval_samples_per_second": 22.45, | |
| "eval_steps_per_second": 2.807, | |
| "eval_wer": 0.9705800721620872, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 16.22340425531915, | |
| "eval_cer": 0.18025766278858632, | |
| "eval_loss": 0.35049712657928467, | |
| "eval_runtime": 218.4181, | |
| "eval_samples_per_second": 22.704, | |
| "eval_steps_per_second": 2.839, | |
| "eval_wer": 0.9782126006106022, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 16.48936170212766, | |
| "eval_cer": 0.17667040155182265, | |
| "eval_loss": 0.34669336676597595, | |
| "eval_runtime": 220.5862, | |
| "eval_samples_per_second": 22.481, | |
| "eval_steps_per_second": 2.811, | |
| "eval_wer": 0.9736330835414932, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 16.75531914893617, | |
| "eval_cer": 0.17923462902847223, | |
| "eval_loss": 0.36808422207832336, | |
| "eval_runtime": 219.3778, | |
| "eval_samples_per_second": 22.605, | |
| "eval_steps_per_second": 2.826, | |
| "eval_wer": 0.9945878434637802, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 17.02127659574468, | |
| "eval_cer": 0.17693612460639774, | |
| "eval_loss": 0.35571783781051636, | |
| "eval_runtime": 218.8646, | |
| "eval_samples_per_second": 22.658, | |
| "eval_steps_per_second": 2.833, | |
| "eval_wer": 1.0104079933388843, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 17.28723404255319, | |
| "grad_norm": 1.837514877319336, | |
| "learning_rate": 0.000155904, | |
| "loss": 0.1749, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 17.28723404255319, | |
| "eval_cer": 0.17874747009508457, | |
| "eval_loss": 0.3445756435394287, | |
| "eval_runtime": 220.0286, | |
| "eval_samples_per_second": 22.538, | |
| "eval_steps_per_second": 2.818, | |
| "eval_wer": 0.9769636414099362, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 17.5531914893617, | |
| "eval_cer": 0.18034180842253508, | |
| "eval_loss": 0.34961050748825073, | |
| "eval_runtime": 216.6863, | |
| "eval_samples_per_second": 22.886, | |
| "eval_steps_per_second": 2.861, | |
| "eval_wer": 0.983902303635859, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 17.819148936170212, | |
| "eval_cer": 0.18056324430134765, | |
| "eval_loss": 0.3584659695625305, | |
| "eval_runtime": 217.6982, | |
| "eval_samples_per_second": 22.779, | |
| "eval_steps_per_second": 2.848, | |
| "eval_wer": 1.0012489592006661, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 18.085106382978722, | |
| "eval_cer": 0.17987236435945245, | |
| "eval_loss": 0.35618793964385986, | |
| "eval_runtime": 217.2896, | |
| "eval_samples_per_second": 22.822, | |
| "eval_steps_per_second": 2.853, | |
| "eval_wer": 0.9716902581182348, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 18.351063829787233, | |
| "eval_cer": 0.18354819994774113, | |
| "eval_loss": 0.3722291588783264, | |
| "eval_runtime": 217.7923, | |
| "eval_samples_per_second": 22.769, | |
| "eval_steps_per_second": 2.847, | |
| "eval_wer": 1.0503746877601998, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 18.617021276595743, | |
| "grad_norm": 5.107634544372559, | |
| "learning_rate": 0.00016790399999999997, | |
| "loss": 0.1717, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.617021276595743, | |
| "eval_cer": 0.18089982683714276, | |
| "eval_loss": 0.3554377853870392, | |
| "eval_runtime": 218.5289, | |
| "eval_samples_per_second": 22.693, | |
| "eval_steps_per_second": 2.837, | |
| "eval_wer": 0.9772411878989731, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.882978723404257, | |
| "eval_cer": 0.1788094721411521, | |
| "eval_loss": 0.36780402064323425, | |
| "eval_runtime": 216.2085, | |
| "eval_samples_per_second": 22.936, | |
| "eval_steps_per_second": 2.868, | |
| "eval_wer": 0.9683597002497918, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 19.148936170212767, | |
| "eval_cer": 0.18539497517703799, | |
| "eval_loss": 0.49383628368377686, | |
| "eval_runtime": 219.4656, | |
| "eval_samples_per_second": 22.596, | |
| "eval_steps_per_second": 2.825, | |
| "eval_wer": 1.041909519844574, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 19.414893617021278, | |
| "eval_cer": 0.18054552943104266, | |
| "eval_loss": 0.3926149308681488, | |
| "eval_runtime": 216.1405, | |
| "eval_samples_per_second": 22.943, | |
| "eval_steps_per_second": 2.869, | |
| "eval_wer": 0.9826533444351929, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 19.680851063829788, | |
| "eval_cer": 0.1819007170093756, | |
| "eval_loss": 0.3581140339374542, | |
| "eval_runtime": 217.0297, | |
| "eval_samples_per_second": 22.849, | |
| "eval_steps_per_second": 2.857, | |
| "eval_wer": 1.0001387732445184, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 19.9468085106383, | |
| "grad_norm": 1.7489858865737915, | |
| "learning_rate": 0.000179904, | |
| "loss": 0.1715, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 19.9468085106383, | |
| "eval_cer": 0.18397778555263752, | |
| "eval_loss": 0.35685011744499207, | |
| "eval_runtime": 219.4728, | |
| "eval_samples_per_second": 22.595, | |
| "eval_steps_per_second": 2.825, | |
| "eval_wer": 0.9929225645295587, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 20.21276595744681, | |
| "eval_cer": 0.18136927090022542, | |
| "eval_loss": 0.3910757303237915, | |
| "eval_runtime": 217.6276, | |
| "eval_samples_per_second": 22.787, | |
| "eval_steps_per_second": 2.849, | |
| "eval_wer": 0.9969469886205939, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 20.47872340425532, | |
| "eval_cer": 0.18082896735592274, | |
| "eval_loss": 0.39733073115348816, | |
| "eval_runtime": 218.1385, | |
| "eval_samples_per_second": 22.733, | |
| "eval_steps_per_second": 2.842, | |
| "eval_wer": 1.0016652789342215, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 20.74468085106383, | |
| "eval_cer": 0.18392906965929876, | |
| "eval_loss": 0.3943112790584564, | |
| "eval_runtime": 217.3912, | |
| "eval_samples_per_second": 22.811, | |
| "eval_steps_per_second": 2.852, | |
| "eval_wer": 0.9723841243408271, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 21.01063829787234, | |
| "eval_cer": 0.18227715800335698, | |
| "eval_loss": 0.3984341025352478, | |
| "eval_runtime": 216.5247, | |
| "eval_samples_per_second": 22.903, | |
| "eval_steps_per_second": 2.863, | |
| "eval_wer": 0.9764085484318623, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 21.27659574468085, | |
| "grad_norm": 1.9202663898468018, | |
| "learning_rate": 0.00019190399999999998, | |
| "loss": 0.1667, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 21.27659574468085, | |
| "eval_cer": 0.18395121324718, | |
| "eval_loss": 0.4305620491504669, | |
| "eval_runtime": 219.6412, | |
| "eval_samples_per_second": 22.578, | |
| "eval_steps_per_second": 2.823, | |
| "eval_wer": 1.0499583680266444, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 21.54255319148936, | |
| "eval_cer": 0.1881762098149239, | |
| "eval_loss": 0.37944892048835754, | |
| "eval_runtime": 214.5629, | |
| "eval_samples_per_second": 23.112, | |
| "eval_steps_per_second": 2.89, | |
| "eval_wer": 0.9728004440743825, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 21.80851063829787, | |
| "eval_cer": 0.18339762355014858, | |
| "eval_loss": 0.3965916037559509, | |
| "eval_runtime": 214.8413, | |
| "eval_samples_per_second": 23.082, | |
| "eval_steps_per_second": 2.886, | |
| "eval_wer": 0.9912572855953372, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 22.074468085106382, | |
| "eval_cer": 0.18381392300231622, | |
| "eval_loss": 0.39811334013938904, | |
| "eval_runtime": 215.0561, | |
| "eval_samples_per_second": 23.059, | |
| "eval_steps_per_second": 2.883, | |
| "eval_wer": 0.9744657230086039, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 22.340425531914892, | |
| "eval_cer": 0.18262702669188083, | |
| "eval_loss": 0.4328286349773407, | |
| "eval_runtime": 214.1041, | |
| "eval_samples_per_second": 23.162, | |
| "eval_steps_per_second": 2.896, | |
| "eval_wer": 0.9926450180405217, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 22.606382978723403, | |
| "grad_norm": 2.1760590076446533, | |
| "learning_rate": 0.00020387999999999998, | |
| "loss": 0.1625, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 22.606382978723403, | |
| "eval_cer": 0.18350834148955486, | |
| "eval_loss": 0.4087058901786804, | |
| "eval_runtime": 215.1826, | |
| "eval_samples_per_second": 23.046, | |
| "eval_steps_per_second": 2.881, | |
| "eval_wer": 0.9709963918956426, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 22.872340425531917, | |
| "eval_cer": 0.18611685614196696, | |
| "eval_loss": 0.4149414300918579, | |
| "eval_runtime": 214.9057, | |
| "eval_samples_per_second": 23.075, | |
| "eval_steps_per_second": 2.885, | |
| "eval_wer": 1.0062447960033305, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 23.138297872340427, | |
| "eval_cer": 0.18750304474333368, | |
| "eval_loss": 0.4106564223766327, | |
| "eval_runtime": 214.2659, | |
| "eval_samples_per_second": 23.144, | |
| "eval_steps_per_second": 2.894, | |
| "eval_wer": 0.992089925062448, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 23.404255319148938, | |
| "eval_cer": 0.18692731145842098, | |
| "eval_loss": 0.41398727893829346, | |
| "eval_runtime": 214.1566, | |
| "eval_samples_per_second": 23.156, | |
| "eval_steps_per_second": 2.895, | |
| "eval_wer": 0.9834859839023037, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 23.670212765957448, | |
| "eval_cer": 0.18904423845986917, | |
| "eval_loss": 0.40873560309410095, | |
| "eval_runtime": 213.9242, | |
| "eval_samples_per_second": 23.181, | |
| "eval_steps_per_second": 2.898, | |
| "eval_wer": 0.9918123785734111, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 23.93617021276596, | |
| "grad_norm": 1.4986417293548584, | |
| "learning_rate": 0.00021588, | |
| "loss": 0.1647, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 23.93617021276596, | |
| "eval_cer": 0.1869538837638785, | |
| "eval_loss": 0.4083107113838196, | |
| "eval_runtime": 229.7373, | |
| "eval_samples_per_second": 21.586, | |
| "eval_steps_per_second": 2.699, | |
| "eval_wer": 0.984179850124896, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 24.20212765957447, | |
| "eval_cer": 0.18472181010544778, | |
| "eval_loss": 0.40058091282844543, | |
| "eval_runtime": 215.0023, | |
| "eval_samples_per_second": 23.065, | |
| "eval_steps_per_second": 2.884, | |
| "eval_wer": 0.9858451290591174, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 24.46808510638298, | |
| "eval_cer": 0.18496096085456534, | |
| "eval_loss": 0.4137335419654846, | |
| "eval_runtime": 233.293, | |
| "eval_samples_per_second": 21.257, | |
| "eval_steps_per_second": 2.658, | |
| "eval_wer": 1.001526505689703, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 24.73404255319149, | |
| "eval_cer": 0.1906208619170147, | |
| "eval_loss": 0.4106745719909668, | |
| "eval_runtime": 218.151, | |
| "eval_samples_per_second": 22.732, | |
| "eval_steps_per_second": 2.842, | |
| "eval_wer": 0.9994449070219261, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_cer": 0.19122759622496113, | |
| "eval_loss": 0.42086583375930786, | |
| "eval_runtime": 214.8363, | |
| "eval_samples_per_second": 23.083, | |
| "eval_steps_per_second": 2.886, | |
| "eval_wer": 0.9843186233694143, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 25.26595744680851, | |
| "grad_norm": 6.019426345825195, | |
| "learning_rate": 0.00022785599999999997, | |
| "loss": 0.1667, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 25.26595744680851, | |
| "eval_cer": 0.18928338920898674, | |
| "eval_loss": 0.4373093247413635, | |
| "eval_runtime": 214.1648, | |
| "eval_samples_per_second": 23.155, | |
| "eval_steps_per_second": 2.895, | |
| "eval_wer": 0.9956980294199278, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 25.53191489361702, | |
| "eval_cer": 0.18901766615441168, | |
| "eval_loss": 0.43900319933891296, | |
| "eval_runtime": 216.3618, | |
| "eval_samples_per_second": 22.92, | |
| "eval_steps_per_second": 2.866, | |
| "eval_wer": 0.9822370247016375, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 25.79787234042553, | |
| "eval_cer": 0.19637376604856532, | |
| "eval_loss": 0.4538724422454834, | |
| "eval_runtime": 220.7821, | |
| "eval_samples_per_second": 22.461, | |
| "eval_steps_per_second": 2.808, | |
| "eval_wer": 0.985706355814599, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 26.06382978723404, | |
| "eval_cer": 0.19334895194398558, | |
| "eval_loss": 0.43809235095977783, | |
| "eval_runtime": 213.8497, | |
| "eval_samples_per_second": 23.189, | |
| "eval_steps_per_second": 2.899, | |
| "eval_wer": 1.0037468776019984, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 26.329787234042552, | |
| "eval_cer": 0.18651101200625336, | |
| "eval_loss": 0.4227481782436371, | |
| "eval_runtime": 219.4755, | |
| "eval_samples_per_second": 22.595, | |
| "eval_steps_per_second": 2.825, | |
| "eval_wer": 0.9875104079933389, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 26.595744680851062, | |
| "grad_norm": 3.2743945121765137, | |
| "learning_rate": 0.000239856, | |
| "loss": 0.1644, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 26.595744680851062, | |
| "eval_cer": 0.18837107338827896, | |
| "eval_loss": 0.4802379012107849, | |
| "eval_runtime": 214.7366, | |
| "eval_samples_per_second": 23.093, | |
| "eval_steps_per_second": 2.887, | |
| "eval_wer": 1.0266444629475437, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 26.861702127659573, | |
| "eval_cer": 0.19581131891638137, | |
| "eval_loss": 0.4389278292655945, | |
| "eval_runtime": 217.9698, | |
| "eval_samples_per_second": 22.751, | |
| "eval_steps_per_second": 2.844, | |
| "eval_wer": 0.9950041631973355, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 27.127659574468087, | |
| "eval_cer": 0.19391139907616953, | |
| "eval_loss": 0.4744134247303009, | |
| "eval_runtime": 217.5599, | |
| "eval_samples_per_second": 22.794, | |
| "eval_steps_per_second": 2.85, | |
| "eval_wer": 0.9827921176797113, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 27.393617021276597, | |
| "eval_cer": 0.1983356879348447, | |
| "eval_loss": 0.4494173526763916, | |
| "eval_runtime": 214.0697, | |
| "eval_samples_per_second": 23.165, | |
| "eval_steps_per_second": 2.896, | |
| "eval_wer": 1.0005550929780738, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 27.659574468085108, | |
| "eval_cer": 0.19612132914671898, | |
| "eval_loss": 0.44136643409729004, | |
| "eval_runtime": 214.2461, | |
| "eval_samples_per_second": 23.146, | |
| "eval_steps_per_second": 2.894, | |
| "eval_wer": 0.9962531223980017, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 27.925531914893618, | |
| "grad_norm": 5.488828659057617, | |
| "learning_rate": 0.000251856, | |
| "loss": 0.1742, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 27.925531914893618, | |
| "eval_cer": 0.19315851708820678, | |
| "eval_loss": 0.46681222319602966, | |
| "eval_runtime": 214.6029, | |
| "eval_samples_per_second": 23.108, | |
| "eval_steps_per_second": 2.889, | |
| "eval_wer": 0.9764085484318623, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 28.19148936170213, | |
| "eval_cer": 0.18782634112640004, | |
| "eval_loss": 0.42840632796287537, | |
| "eval_runtime": 214.4792, | |
| "eval_samples_per_second": 23.121, | |
| "eval_steps_per_second": 2.891, | |
| "eval_wer": 0.9719678046072717, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 28.45744680851064, | |
| "eval_cer": 0.1943764144216759, | |
| "eval_loss": 0.4257587492465973, | |
| "eval_runtime": 214.0589, | |
| "eval_samples_per_second": 23.167, | |
| "eval_steps_per_second": 2.896, | |
| "eval_wer": 1.02789342214821, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 28.72340425531915, | |
| "eval_cer": 0.18916381383442796, | |
| "eval_loss": 0.4250844120979309, | |
| "eval_runtime": 228.7764, | |
| "eval_samples_per_second": 21.676, | |
| "eval_steps_per_second": 2.71, | |
| "eval_wer": 1.0023591451568137, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 28.98936170212766, | |
| "eval_cer": 0.19779538439054203, | |
| "eval_loss": 0.4596838653087616, | |
| "eval_runtime": 214.1002, | |
| "eval_samples_per_second": 23.162, | |
| "eval_steps_per_second": 2.896, | |
| "eval_wer": 1.0201221204551763, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 29.25531914893617, | |
| "grad_norm": 4.931338787078857, | |
| "learning_rate": 0.000263832, | |
| "loss": 0.1669, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 29.25531914893617, | |
| "eval_cer": 0.1918786177086701, | |
| "eval_loss": 0.4414420425891876, | |
| "eval_runtime": 214.9531, | |
| "eval_samples_per_second": 23.07, | |
| "eval_steps_per_second": 2.884, | |
| "eval_wer": 0.9879267277268943, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 29.52127659574468, | |
| "eval_cer": 0.19090429984189478, | |
| "eval_loss": 0.4472629725933075, | |
| "eval_runtime": 220.3712, | |
| "eval_samples_per_second": 22.503, | |
| "eval_steps_per_second": 2.813, | |
| "eval_wer": 0.9772411878989731, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 29.78723404255319, | |
| "eval_cer": 0.19330466476822306, | |
| "eval_loss": 0.45273834466934204, | |
| "eval_runtime": 214.7179, | |
| "eval_samples_per_second": 23.095, | |
| "eval_steps_per_second": 2.888, | |
| "eval_wer": 0.9944490702192618, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 11280, | |
| "total_flos": 1.5765326864839811e+19, | |
| "train_loss": 0.910362657587579, | |
| "train_runtime": 61619.102, | |
| "train_samples_per_second": 5.857, | |
| "train_steps_per_second": 0.183 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 11280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5765326864839811e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |