| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.05017317232987, | |
| "global_step": 172000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002958, | |
| "loss": 3.155, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002999769241570842, | |
| "loss": 0.338, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00029995352066528323, | |
| "loss": 0.327, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029993011717348224, | |
| "loss": 0.3225, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029990671368168126, | |
| "loss": 0.3079, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00029988331018988027, | |
| "loss": 0.3309, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00029985990669807933, | |
| "loss": 0.2943, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00029983650320627834, | |
| "loss": 0.2795, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_cer": 0.05897733717227239, | |
| "eval_loss": 0.22565825283527374, | |
| "eval_runtime": 1455.9056, | |
| "eval_samples_per_second": 13.045, | |
| "eval_steps_per_second": 3.262, | |
| "eval_wer": 0.20478772194834444, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002998130997144774, | |
| "loss": 0.2896, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002997896962226764, | |
| "loss": 0.2735, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00029976629273087543, | |
| "loss": 0.281, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00029974288923907444, | |
| "loss": 0.2755, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00029971948574727345, | |
| "loss": 0.2831, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002996961290624561, | |
| "loss": 0.2708, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002996727255706551, | |
| "loss": 0.2667, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002996493220788541, | |
| "loss": 0.2582, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_cer": 0.05252843759542817, | |
| "eval_loss": 0.20639470219612122, | |
| "eval_runtime": 1350.2359, | |
| "eval_samples_per_second": 14.066, | |
| "eval_steps_per_second": 3.517, | |
| "eval_wer": 0.18800766597579208, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002996259185870532, | |
| "loss": 0.2874, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002996025150952522, | |
| "loss": 0.2585, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002995791116034512, | |
| "loss": 0.2579, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002995557081116502, | |
| "loss": 0.2664, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00029953230461984923, | |
| "loss": 0.2702, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00029950890112804824, | |
| "loss": 0.2487, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002994854976362473, | |
| "loss": 0.2501, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002994620941444463, | |
| "loss": 0.2485, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_cer": 0.04427867207608079, | |
| "eval_loss": 0.16677920520305634, | |
| "eval_runtime": 1348.5895, | |
| "eval_samples_per_second": 14.084, | |
| "eval_steps_per_second": 3.521, | |
| "eval_wer": 0.15644211290530335, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002994386906526454, | |
| "loss": 0.2546, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.000299415333967828, | |
| "loss": 0.2376, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.000299391930476027, | |
| "loss": 0.2451, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.000299368526984226, | |
| "loss": 0.2436, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.000299345123492425, | |
| "loss": 0.2405, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002993217200006241, | |
| "loss": 0.2447, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002992983165088231, | |
| "loss": 0.2415, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002992749130170221, | |
| "loss": 0.2379, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_cer": 0.04885581621079265, | |
| "eval_loss": 0.1717624068260193, | |
| "eval_runtime": 1346.3358, | |
| "eval_samples_per_second": 14.107, | |
| "eval_steps_per_second": 3.527, | |
| "eval_wer": 0.17038060554963563, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00029925150952522117, | |
| "loss": 0.2462, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002992281060334202, | |
| "loss": 0.2305, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002992047025416192, | |
| "loss": 0.2333, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002991812990498182, | |
| "loss": 0.2243, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00029915794236500085, | |
| "loss": 0.2182, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00029913453887319986, | |
| "loss": 0.2347, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00029911113538139887, | |
| "loss": 0.2178, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00029908773188959794, | |
| "loss": 0.2313, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_cer": 0.04552196483880818, | |
| "eval_loss": 0.166758194565773, | |
| "eval_runtime": 1346.4361, | |
| "eval_samples_per_second": 14.106, | |
| "eval_steps_per_second": 3.527, | |
| "eval_wer": 0.1609425559237618, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00029906432839779695, | |
| "loss": 0.2118, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00029904092490599596, | |
| "loss": 0.2437, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00029901752141419497, | |
| "loss": 0.2139, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00029899416472937756, | |
| "loss": 0.2157, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00029897076123757663, | |
| "loss": 0.211, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00029894735774577564, | |
| "loss": 0.2121, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00029892395425397465, | |
| "loss": 0.2066, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002989005507621737, | |
| "loss": 0.2047, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_cer": 0.04369247044453169, | |
| "eval_loss": 0.15543465316295624, | |
| "eval_runtime": 1348.2816, | |
| "eval_samples_per_second": 14.087, | |
| "eval_steps_per_second": 3.522, | |
| "eval_wer": 0.14927965588980355, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00029887714727037273, | |
| "loss": 0.2077, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00029885374377857174, | |
| "loss": 0.201, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00029883034028677075, | |
| "loss": 0.207, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00029880693679496976, | |
| "loss": 0.1931, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002987835801101524, | |
| "loss": 0.2115, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002987601766183514, | |
| "loss": 0.2226, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002987367731265505, | |
| "loss": 0.2106, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002987133696347495, | |
| "loss": 0.2055, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_cer": 0.049039174628102776, | |
| "eval_loss": 0.16633369028568268, | |
| "eval_runtime": 1346.0932, | |
| "eval_samples_per_second": 14.11, | |
| "eval_steps_per_second": 3.528, | |
| "eval_wer": 0.16584113006787746, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002986900129499321, | |
| "loss": 0.2178, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002986666094581311, | |
| "loss": 0.2125, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002986432059663301, | |
| "loss": 0.2029, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002986198024745292, | |
| "loss": 0.2104, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002985963989827282, | |
| "loss": 0.2034, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00029857304229791084, | |
| "loss": 0.2116, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00029854963880610985, | |
| "loss": 0.2059, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00029852623531430886, | |
| "loss": 0.205, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_cer": 0.04317034201457052, | |
| "eval_loss": 0.14783667027950287, | |
| "eval_runtime": 1347.0872, | |
| "eval_samples_per_second": 14.099, | |
| "eval_steps_per_second": 3.525, | |
| "eval_wer": 0.15488081437331427, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00029850283182250787, | |
| "loss": 0.2225, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002984794751376905, | |
| "loss": 0.2011, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00029845607164588953, | |
| "loss": 0.2011, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002984327149610722, | |
| "loss": 0.1957, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002984093114692712, | |
| "loss": 0.2044, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00029838590797747025, | |
| "loss": 0.2011, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00029836250448566926, | |
| "loss": 0.2046, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002983391009938683, | |
| "loss": 0.2017, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_cer": 0.04304628539021943, | |
| "eval_loss": 0.14913983643054962, | |
| "eval_runtime": 1406.2309, | |
| "eval_samples_per_second": 13.506, | |
| "eval_steps_per_second": 3.377, | |
| "eval_wer": 0.1499119817952591, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002983156975020673, | |
| "loss": 0.2028, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002982922940102663, | |
| "loss": 0.1991, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002982688905184653, | |
| "loss": 0.2145, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00029824553383364796, | |
| "loss": 0.2043, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00029822213034184697, | |
| "loss": 0.194, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00029819872685004603, | |
| "loss": 0.2006, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00029817532335824504, | |
| "loss": 0.2095, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00029815196667342764, | |
| "loss": 0.1975, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_cer": 0.0433755125856127, | |
| "eval_loss": 0.14519542455673218, | |
| "eval_runtime": 1370.9335, | |
| "eval_samples_per_second": 13.854, | |
| "eval_steps_per_second": 3.464, | |
| "eval_wer": 0.14985343310030952, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00029812856318162665, | |
| "loss": 0.2033, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002981051596898257, | |
| "loss": 0.1975, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002980817561980247, | |
| "loss": 0.1945, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00029805835270622374, | |
| "loss": 0.1939, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002980349492144228, | |
| "loss": 0.2073, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002980115925296054, | |
| "loss": 0.193, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002979881890378044, | |
| "loss": 0.1895, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.002979647855460034, | |
| "loss": 0.1882, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_cer": 0.04118611765475723, | |
| "eval_loss": 0.1441776603460312, | |
| "eval_runtime": 1437.09, | |
| "eval_samples_per_second": 13.216, | |
| "eval_steps_per_second": 3.305, | |
| "eval_wer": 0.14381901427417182, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00029794138205420243, | |
| "loss": 0.1814, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002979179785624015, | |
| "loss": 0.1857, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002978945750706005, | |
| "loss": 0.193, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0002978711715787995, | |
| "loss": 0.1835, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002978477680869986, | |
| "loss": 0.171, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002978243645951976, | |
| "loss": 0.1777, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002978010079103802, | |
| "loss": 0.1701, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002977776044185792, | |
| "loss": 0.1821, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_cer": 0.04377358439122279, | |
| "eval_loss": 0.14771120250225067, | |
| "eval_runtime": 1168.4306, | |
| "eval_samples_per_second": 16.255, | |
| "eval_steps_per_second": 4.064, | |
| "eval_wer": 0.1521368322033435, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00029775420092677826, | |
| "loss": 0.1878, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0002977307974349773, | |
| "loss": 0.1848, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002977073939431763, | |
| "loss": 0.1837, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00029768403725835893, | |
| "loss": 0.1736, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00029766063376655794, | |
| "loss": 0.1805, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.00029763723027475696, | |
| "loss": 0.1795, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00029761382678295597, | |
| "loss": 0.1752, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.000297590423291155, | |
| "loss": 0.1848, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_cer": 0.04313966867338481, | |
| "eval_loss": 0.13986873626708984, | |
| "eval_runtime": 1079.4763, | |
| "eval_samples_per_second": 17.595, | |
| "eval_steps_per_second": 4.399, | |
| "eval_wer": 0.14816332743943136, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002975670666063376, | |
| "loss": 0.1873, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002975436631145367, | |
| "loss": 0.1848, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002975202596227357, | |
| "loss": 0.1953, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002974968561309347, | |
| "loss": 0.1779, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002974734526391337, | |
| "loss": 0.1861, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00029745004914733274, | |
| "loss": 0.1784, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002974266924625154, | |
| "loss": 0.1902, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002974032889707144, | |
| "loss": 0.1852, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_cer": 0.041413782009335605, | |
| "eval_loss": 0.14103934168815613, | |
| "eval_runtime": 1043.4328, | |
| "eval_samples_per_second": 18.202, | |
| "eval_steps_per_second": 4.551, | |
| "eval_wer": 0.1456340238176091, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002973798854789134, | |
| "loss": 0.1758, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00029735648198711247, | |
| "loss": 0.1799, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00029733312530229506, | |
| "loss": 0.177, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00029730972181049413, | |
| "loss": 0.176, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00029728631831869314, | |
| "loss": 0.1852, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00029726296163387573, | |
| "loss": 0.1813, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.00029723955814207474, | |
| "loss": 0.1879, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0002972161546502738, | |
| "loss": 0.173, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_cer": 0.039124869127077605, | |
| "eval_loss": 0.13692142069339752, | |
| "eval_runtime": 1043.8955, | |
| "eval_samples_per_second": 18.194, | |
| "eval_steps_per_second": 4.549, | |
| "eval_wer": 0.13655507285409274, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002971927511584728, | |
| "loss": 0.17, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00029716934766667183, | |
| "loss": 0.1885, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002971459441748709, | |
| "loss": 0.1885, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002971225874900535, | |
| "loss": 0.1775, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002970991839982525, | |
| "loss": 0.184, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0002970757805064515, | |
| "loss": 0.1865, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0002970523770146505, | |
| "loss": 0.177, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0002970289735228496, | |
| "loss": 0.1766, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_cer": 0.043919453169305935, | |
| "eval_loss": 0.14147880673408508, | |
| "eval_runtime": 1043.0346, | |
| "eval_samples_per_second": 18.209, | |
| "eval_steps_per_second": 4.553, | |
| "eval_wer": 0.14889323450313627, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0002970055700310486, | |
| "loss": 0.1751, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.00029698216653924767, | |
| "loss": 0.16, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0002969587630474467, | |
| "loss": 0.1654, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00029693540636262927, | |
| "loss": 0.169, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0002969120028708283, | |
| "loss": 0.1668, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0002968885993790273, | |
| "loss": 0.1555, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00029686519588722636, | |
| "loss": 0.1643, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00029684179239542537, | |
| "loss": 0.1651, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_cer": 0.04225832133664878, | |
| "eval_loss": 0.14033427834510803, | |
| "eval_runtime": 1043.9782, | |
| "eval_samples_per_second": 18.193, | |
| "eval_steps_per_second": 4.549, | |
| "eval_wer": 0.1446074700328263, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0002968183889036244, | |
| "loss": 0.181, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.00029679507902579067, | |
| "loss": 0.1691, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0002967716755339897, | |
| "loss": 0.159, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0002967482720421887, | |
| "loss": 0.171, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0002967248685503877, | |
| "loss": 0.1529, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.0002967014650585867, | |
| "loss": 0.1714, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.0002966780615667857, | |
| "loss": 0.1646, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 0.0002966546580749848, | |
| "loss": 0.1648, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_cer": 0.04023797059721677, | |
| "eval_loss": 0.13524918258190155, | |
| "eval_runtime": 1043.0033, | |
| "eval_samples_per_second": 18.21, | |
| "eval_steps_per_second": 4.553, | |
| "eval_wer": 0.1384325343388096, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0002966312545831838, | |
| "loss": 0.1855, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00029660789789836645, | |
| "loss": 0.173, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.00029658449440656546, | |
| "loss": 0.1811, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.00029656109091476447, | |
| "loss": 0.1772, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0002965376874229635, | |
| "loss": 0.1683, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.0002965142839311625, | |
| "loss": 0.1689, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.0002964908804393615, | |
| "loss": 0.1541, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0002964675705615278, | |
| "loss": 0.1541, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_cer": 0.0414948959560267, | |
| "eval_loss": 0.13895024359226227, | |
| "eval_runtime": 1042.4783, | |
| "eval_samples_per_second": 18.219, | |
| "eval_steps_per_second": 4.555, | |
| "eval_wer": 0.1431398494127566, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0002964441670697268, | |
| "loss": 0.1739, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0002964207635779258, | |
| "loss": 0.1671, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.0002963973600861248, | |
| "loss": 0.168, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.00029637395659432383, | |
| "loss": 0.1611, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00029635055310252284, | |
| "loss": 0.1654, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.0002963271964177055, | |
| "loss": 0.1714, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.0002963037929259045, | |
| "loss": 0.1735, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.00029628038943410357, | |
| "loss": 0.1634, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_cer": 0.04235443113903067, | |
| "eval_loss": 0.1428999900817871, | |
| "eval_runtime": 1074.2691, | |
| "eval_samples_per_second": 17.68, | |
| "eval_steps_per_second": 4.421, | |
| "eval_wer": 0.1467074165583516, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.0002962569859423026, | |
| "loss": 0.163, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 0.00029623362925748517, | |
| "loss": 0.1672, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.0002962102257656842, | |
| "loss": 0.1651, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00029618682227388325, | |
| "loss": 0.1653, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.00029616341878208226, | |
| "loss": 0.163, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.00029614001529028127, | |
| "loss": 0.1681, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00029611661179848033, | |
| "loss": 0.1608, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00029609325511366293, | |
| "loss": 0.1649, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_cer": 0.03920121166513982, | |
| "eval_loss": 0.13187673687934875, | |
| "eval_runtime": 1043.8537, | |
| "eval_samples_per_second": 18.195, | |
| "eval_steps_per_second": 4.549, | |
| "eval_wer": 0.13773775649207445, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00029606985162186194, | |
| "loss": 0.1629, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00029604644813006095, | |
| "loss": 0.1671, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00029602304463825996, | |
| "loss": 0.1693, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.000295999641146459, | |
| "loss": 0.1524, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0002959762844616417, | |
| "loss": 0.1639, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0002959528809698407, | |
| "loss": 0.1633, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.0002959294774780397, | |
| "loss": 0.1557, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.0002959060739862387, | |
| "loss": 0.1571, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_cer": 0.039078518300396985, | |
| "eval_loss": 0.1323617696762085, | |
| "eval_runtime": 1041.314, | |
| "eval_samples_per_second": 18.239, | |
| "eval_steps_per_second": 4.561, | |
| "eval_wer": 0.13669168647564178, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0002958826704944377, | |
| "loss": 0.1626, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.00029585926700263673, | |
| "loss": 0.1515, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0002958358635108358, | |
| "loss": 0.1445, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.0002958124600190348, | |
| "loss": 0.1554, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 0.00029578910333421745, | |
| "loss": 0.1559, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.00029576574664940005, | |
| "loss": 0.1716, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.0002957423431575991, | |
| "loss": 0.1524, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.0002957189396657981, | |
| "loss": 0.1483, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_cer": 0.03799609017144353, | |
| "eval_loss": 0.12687690556049347, | |
| "eval_runtime": 1041.0565, | |
| "eval_samples_per_second": 18.244, | |
| "eval_steps_per_second": 4.562, | |
| "eval_wer": 0.13329195892223564, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.00029569553617399714, | |
| "loss": 0.1623, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.00029567213268219615, | |
| "loss": 0.1499, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.0002956487759973788, | |
| "loss": 0.1474, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.0002956253725055778, | |
| "loss": 0.1519, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.0002956019690137768, | |
| "loss": 0.1567, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.0002955785655219759, | |
| "loss": 0.1596, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0002955551620301749, | |
| "loss": 0.1524, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.0002955317585383739, | |
| "loss": 0.1483, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_cer": 0.03884608253718972, | |
| "eval_loss": 0.13216418027877808, | |
| "eval_runtime": 1043.5586, | |
| "eval_samples_per_second": 18.2, | |
| "eval_steps_per_second": 4.551, | |
| "eval_wer": 0.1352787113041917, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0002955084018535565, | |
| "loss": 0.1509, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.0002954849983617555, | |
| "loss": 0.1553, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.0002954615948699546, | |
| "loss": 0.1576, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.0002954381913781536, | |
| "loss": 0.157, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 0.00029541478788635265, | |
| "loss": 0.1641, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.00029539138439455166, | |
| "loss": 0.1631, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.0002953679809027507, | |
| "loss": 0.1619, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0002953445774109497, | |
| "loss": 0.1502, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_cer": 0.038923106705056054, | |
| "eval_loss": 0.12758338451385498, | |
| "eval_runtime": 1042.7138, | |
| "eval_samples_per_second": 18.215, | |
| "eval_steps_per_second": 4.554, | |
| "eval_wer": 0.13328415242957567, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.0002953212207261323, | |
| "loss": 0.1508, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.00029529781723433134, | |
| "loss": 0.1423, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.00029527441374253035, | |
| "loss": 0.1619, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.00029525101025072937, | |
| "loss": 0.1483, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.000295227653565912, | |
| "loss": 0.1716, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 0.000295204250074111, | |
| "loss": 0.1461, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00029518084658231004, | |
| "loss": 0.1455, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.00029515744309050905, | |
| "loss": 0.1523, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_cer": 0.03784408672512324, | |
| "eval_loss": 0.1300228387117386, | |
| "eval_runtime": 1048.2511, | |
| "eval_samples_per_second": 18.119, | |
| "eval_steps_per_second": 4.53, | |
| "eval_wer": 0.12833483608317037, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0002951340395987081, | |
| "loss": 0.1646, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.0002951106361069071, | |
| "loss": 0.1519, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.00029508727942208977, | |
| "loss": 0.1516, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.0002950638759302888, | |
| "loss": 0.1675, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.0002950404724384878, | |
| "loss": 0.1474, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.0002950170689466868, | |
| "loss": 0.151, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.0002949936654548858, | |
| "loss": 0.1419, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00029497030877006846, | |
| "loss": 0.139, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_cer": 0.03710792653666623, | |
| "eval_loss": 0.1256220042705536, | |
| "eval_runtime": 1098.0599, | |
| "eval_samples_per_second": 17.297, | |
| "eval_steps_per_second": 4.325, | |
| "eval_wer": 0.12972048853031065, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.0002949469052782675, | |
| "loss": 0.137, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.0002949235017864665, | |
| "loss": 0.141, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00029490009829466555, | |
| "loss": 0.1528, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.0002948767416098482, | |
| "loss": 0.1426, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.0002948533381180472, | |
| "loss": 0.1375, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.0002948299346262462, | |
| "loss": 0.1413, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00029480653113444523, | |
| "loss": 0.1322, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.00029478312764264424, | |
| "loss": 0.1444, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_cer": 0.03732468481437857, | |
| "eval_loss": 0.12207575142383575, | |
| "eval_runtime": 1054.5242, | |
| "eval_samples_per_second": 18.011, | |
| "eval_steps_per_second": 4.503, | |
| "eval_wer": 0.1293418736363033, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00029475972415084325, | |
| "loss": 0.1512, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.0002947363206590423, | |
| "loss": 0.1393, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.00029471291716724133, | |
| "loss": 0.1487, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 0.00029468951367544034, | |
| "loss": 0.1493, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 0.0002946661101836394, | |
| "loss": 0.151, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.0002946427066918384, | |
| "loss": 0.1329, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.00029461930320003743, | |
| "loss": 0.1492, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00029459589970823644, | |
| "loss": 0.1411, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "eval_cer": 0.037894527330628626, | |
| "eval_loss": 0.12310981005430222, | |
| "eval_runtime": 1041.1085, | |
| "eval_samples_per_second": 18.243, | |
| "eval_steps_per_second": 4.561, | |
| "eval_wer": 0.13332708813920538, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.00029457258983040267, | |
| "loss": 0.1431, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0002945491863386017, | |
| "loss": 0.1405, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.00029452578284680075, | |
| "loss": 0.1388, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 0.00029450237935499976, | |
| "loss": 0.1478, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.00029447897586319877, | |
| "loss": 0.1532, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.00029445561917838136, | |
| "loss": 0.1456, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.000294432262493564, | |
| "loss": 0.1511, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 0.000294408859001763, | |
| "loss": 0.1457, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_cer": 0.03661783470749902, | |
| "eval_loss": 0.12026005238294601, | |
| "eval_runtime": 1041.1064, | |
| "eval_samples_per_second": 18.243, | |
| "eval_steps_per_second": 4.561, | |
| "eval_wer": 0.12665253691495218, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 0.0002943854555099621, | |
| "loss": 0.1425, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 0.0002943620520181611, | |
| "loss": 0.1468, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.0002943386485263601, | |
| "loss": 0.1438, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.0002943152450345591, | |
| "loss": 0.1495, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 0.00029429184154275813, | |
| "loss": 0.1407, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 0.00029426843805095714, | |
| "loss": 0.1486, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.0002942450345591562, | |
| "loss": 0.1421, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 0.0002942216310673552, | |
| "loss": 0.1458, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_cer": 0.037944967936134014, | |
| "eval_loss": 0.12521982192993164, | |
| "eval_runtime": 1041.2886, | |
| "eval_samples_per_second": 18.24, | |
| "eval_steps_per_second": 4.561, | |
| "eval_wer": 0.1334519920217645, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 0.00029419827438253787, | |
| "loss": 0.1477, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.0002941748708907369, | |
| "loss": 0.1432, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 0.0002941514673989359, | |
| "loss": 0.1525, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.0002941280639071349, | |
| "loss": 0.1409, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 0.0002941046604153339, | |
| "loss": 0.1485, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 0.000294081256923533, | |
| "loss": 0.1422, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.000294057853431732, | |
| "loss": 0.1438, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 0.00029403449674691464, | |
| "loss": 0.1376, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_cer": 0.03670849147144789, | |
| "eval_loss": 0.12269050627946854, | |
| "eval_runtime": 1041.8258, | |
| "eval_samples_per_second": 18.23, | |
| "eval_steps_per_second": 4.558, | |
| "eval_wer": 0.1273629277470072, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.00029401109325511365, | |
| "loss": 0.1396, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 0.00029398768976331266, | |
| "loss": 0.1314, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.00029396428627151167, | |
| "loss": 0.1401, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0002939408827797107, | |
| "loss": 0.1277, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0002939174792879097, | |
| "loss": 0.1412, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00029389407579610876, | |
| "loss": 0.1353, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00029387071911129135, | |
| "loss": 0.1349, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.0002938473156194904, | |
| "loss": 0.1338, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "eval_cer": 0.036872082624438335, | |
| "eval_loss": 0.1331152617931366, | |
| "eval_runtime": 1042.3485, | |
| "eval_samples_per_second": 18.221, | |
| "eval_steps_per_second": 4.556, | |
| "eval_wer": 0.1286002568336085, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.00029382391212768943, | |
| "loss": 0.1446, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.00029380050863588844, | |
| "loss": 0.1297, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.00029377710514408745, | |
| "loss": 0.1344, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 0.0002937537484592701, | |
| "loss": 0.1349, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.0002937303449674691, | |
| "loss": 0.1249, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 0.0002937069414756681, | |
| "loss": 0.1358, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 0.0002936835379838672, | |
| "loss": 0.1405, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.0002936601344920662, | |
| "loss": 0.1212, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "eval_cer": 0.036793013567159624, | |
| "eval_loss": 0.12496736645698547, | |
| "eval_runtime": 1043.01, | |
| "eval_samples_per_second": 18.21, | |
| "eval_steps_per_second": 4.553, | |
| "eval_wer": 0.12528640069946173, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 0.00029363677780724884, | |
| "loss": 0.1332, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00029361337431544786, | |
| "loss": 0.1396, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 0.00029358997082364687, | |
| "loss": 0.1304, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.0002935665673318459, | |
| "loss": 0.1303, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 0.0002935431638400449, | |
| "loss": 0.1356, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00029351980715522754, | |
| "loss": 0.148, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.00029349640366342655, | |
| "loss": 0.1371, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.0002934730001716256, | |
| "loss": 0.1336, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_cer": 0.03752712886620425, | |
| "eval_loss": 0.12814708054065704, | |
| "eval_runtime": 1042.3272, | |
| "eval_samples_per_second": 18.222, | |
| "eval_steps_per_second": 4.556, | |
| "eval_wer": 0.13243324472964163, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 0.0002934495966798246, | |
| "loss": 0.1489, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 0.00029342619318802364, | |
| "loss": 0.1354, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00029340278969622265, | |
| "loss": 0.1341, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 0.00029337943301140524, | |
| "loss": 0.1403, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0002933560295196043, | |
| "loss": 0.1369, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.0002933326260278033, | |
| "loss": 0.1439, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00029330926934298596, | |
| "loss": 0.1349, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.000293285865851185, | |
| "loss": 0.1345, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_cer": 0.03716995484884177, | |
| "eval_loss": 0.1245645210146904, | |
| "eval_runtime": 1041.9872, | |
| "eval_samples_per_second": 18.228, | |
| "eval_steps_per_second": 4.558, | |
| "eval_wer": 0.13216001748654355, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.000293262462359384, | |
| "loss": 0.1345, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 0.000293239058867583, | |
| "loss": 0.1392, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00029321570218276565, | |
| "loss": 0.1437, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.00029319229869096466, | |
| "loss": 0.1481, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 0.00029316889519916367, | |
| "loss": 0.1301, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.00029314549170736273, | |
| "loss": 0.1358, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 0.00029312208821556174, | |
| "loss": 0.1284, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 0.00029309868472376076, | |
| "loss": 0.1389, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_cer": 0.03524298739257514, | |
| "eval_loss": 0.12240828573703766, | |
| "eval_runtime": 1040.9111, | |
| "eval_samples_per_second": 18.247, | |
| "eval_steps_per_second": 4.562, | |
| "eval_wer": 0.1233660035051152, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.0002930753280389434, | |
| "loss": 0.1344, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 0.0002930519245471424, | |
| "loss": 0.1379, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0002930285210553414, | |
| "loss": 0.1259, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 0.00029300511756354044, | |
| "loss": 0.1204, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.0002929817140717395, | |
| "loss": 0.1293, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 0.0002929583105799385, | |
| "loss": 0.1257, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 0.0002929349070881375, | |
| "loss": 0.1279, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.00029291150359633654, | |
| "loss": 0.126, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_cer": 0.03576238930331981, | |
| "eval_loss": 0.12034807354211807, | |
| "eval_runtime": 1041.2962, | |
| "eval_samples_per_second": 18.24, | |
| "eval_steps_per_second": 4.561, | |
| "eval_wer": 0.12211696467952396, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.0002928881469115192, | |
| "loss": 0.1337, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.0002928647434197182, | |
| "loss": 0.1237, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 0.0002928413399279172, | |
| "loss": 0.1244, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.0002928179364361162, | |
| "loss": 0.1335, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 0.0002927945329443153, | |
| "loss": 0.126, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 0.0002927711762594979, | |
| "loss": 0.1205, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.00029274777276769694, | |
| "loss": 0.1296, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.00029272436927589595, | |
| "loss": 0.1197, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "eval_cer": 0.03777728700431881, | |
| "eval_loss": 0.1192484200000763, | |
| "eval_runtime": 1041.7692, | |
| "eval_samples_per_second": 18.231, | |
| "eval_steps_per_second": 4.559, | |
| "eval_wer": 0.12780789782862406, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 0.00029270096578409496, | |
| "loss": 0.1231, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.000292677562292294, | |
| "loss": 0.1209, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.000292654158800493, | |
| "loss": 0.1332, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 0.0002926308489226592, | |
| "loss": 0.1283, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0002926074454308583, | |
| "loss": 0.1411, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 0.0002925840419390573, | |
| "loss": 0.1318, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.0002925606384472563, | |
| "loss": 0.1259, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 0.0002925372349554553, | |
| "loss": 0.1309, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_cer": 0.035546994285215724, | |
| "eval_loss": 0.11985628306865692, | |
| "eval_runtime": 1041.0069, | |
| "eval_samples_per_second": 18.245, | |
| "eval_steps_per_second": 4.562, | |
| "eval_wer": 0.12378755410875225, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.0002925138314636543, | |
| "loss": 0.1237, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 0.00029249042797185334, | |
| "loss": 0.1363, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.0002924670244800524, | |
| "loss": 0.1275, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0002924436209882514, | |
| "loss": 0.1285, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 0.0002924202174964505, | |
| "loss": 0.1453, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0002923968140046495, | |
| "loss": 0.1273, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.0002923734105128485, | |
| "loss": 0.1352, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 0.0002923500070210475, | |
| "loss": 0.127, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_cer": 0.03588303777865026, | |
| "eval_loss": 0.12572461366653442, | |
| "eval_runtime": 1040.9162, | |
| "eval_samples_per_second": 18.246, | |
| "eval_steps_per_second": 4.562, | |
| "eval_wer": 0.1238812320206716, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 0.0002923266503362301, | |
| "loss": 0.1382, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 0.00029230324684442917, | |
| "loss": 0.1312, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 0.0002922798433526282, | |
| "loss": 0.1342, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 0.00029225648666781083, | |
| "loss": 0.1442, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.00029223308317600984, | |
| "loss": 0.1253, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 0.00029220967968420885, | |
| "loss": 0.1321, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.00029218627619240786, | |
| "loss": 0.1337, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.0002921628727006069, | |
| "loss": 0.1233, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "eval_cer": 0.03597301291279501, | |
| "eval_loss": 0.12973648309707642, | |
| "eval_runtime": 1040.5606, | |
| "eval_samples_per_second": 18.253, | |
| "eval_steps_per_second": 4.564, | |
| "eval_wer": 0.1249936572247138, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.00029213946920880594, | |
| "loss": 0.1334, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.00029211606571700495, | |
| "loss": 0.1323, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.0002920927090321876, | |
| "loss": 0.1329, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.0002920693055403866, | |
| "loss": 0.1306, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.0002920459020485856, | |
| "loss": 0.1397, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00029202249855678463, | |
| "loss": 0.1303, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 0.0002919991418719673, | |
| "loss": 0.1263, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.0002919757383801663, | |
| "loss": 0.1222, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_cer": 0.033454390786546266, | |
| "eval_loss": 0.12292832136154175, | |
| "eval_runtime": 1040.6782, | |
| "eval_samples_per_second": 18.251, | |
| "eval_steps_per_second": 4.563, | |
| "eval_wer": 0.11680074317810123, | |
| "step": 172000 | |
| } | |
| ], | |
| "max_steps": 6409800, | |
| "num_train_epochs": 300, | |
| "total_flos": 2.798604341991718e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |