| { | |
| "best_metric": 1.8990676403045654, | |
| "best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base/checkpoint-496", | |
| "epoch": 199.90140845070422, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 2.043365240097046, | |
| "eval_runtime": 7.4215, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.622568093385214, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4739, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 2.102400064468384, | |
| "eval_runtime": 7.4428, | |
| "eval_samples_per_second": 8.465, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6246632744687219, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0004, | |
| "loss": 0.4693, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 1.9824020862579346, | |
| "eval_runtime": 7.4471, | |
| "eval_samples_per_second": 8.46, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.6210715354684226, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.00039746835443037974, | |
| "loss": 0.5139, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_loss": 2.2961695194244385, | |
| "eval_runtime": 7.4429, | |
| "eval_samples_per_second": 8.464, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6429212810535768, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.0003949367088607595, | |
| "loss": 0.5081, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 2.2200775146484375, | |
| "eval_runtime": 7.4534, | |
| "eval_samples_per_second": 8.452, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.6291529482190961, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "eval_loss": 2.139875888824463, | |
| "eval_runtime": 7.459, | |
| "eval_samples_per_second": 8.446, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.6207722238850644, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 0.0003924050632911393, | |
| "loss": 0.5785, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 2.145110607147217, | |
| "eval_runtime": 7.4526, | |
| "eval_samples_per_second": 8.453, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.6417240347201437, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 0.000389873417721519, | |
| "loss": 0.533, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "eval_loss": 2.118384599685669, | |
| "eval_runtime": 7.4549, | |
| "eval_samples_per_second": 8.451, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.6330439988027536, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 0.00038734177215189877, | |
| "loss": 0.5141, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_loss": 2.02298903465271, | |
| "eval_runtime": 7.4493, | |
| "eval_samples_per_second": 8.457, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.6342412451361867, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0003848101265822785, | |
| "loss": 0.4971, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 2.2136712074279785, | |
| "eval_runtime": 7.4321, | |
| "eval_samples_per_second": 8.477, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6381322957198443, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "eval_loss": 2.1159048080444336, | |
| "eval_runtime": 7.3886, | |
| "eval_samples_per_second": 8.527, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6252618976354385, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 0.00038227848101265825, | |
| "loss": 0.5645, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "eval_loss": 2.096606969833374, | |
| "eval_runtime": 7.4372, | |
| "eval_samples_per_second": 8.471, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6246632744687219, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 0.00037974683544303797, | |
| "loss": 0.4932, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "eval_loss": 1.9248937368392944, | |
| "eval_runtime": 7.4436, | |
| "eval_samples_per_second": 8.464, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6222687818018557, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 0.00037721518987341774, | |
| "loss": 0.4918, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "eval_loss": 2.044543504714966, | |
| "eval_runtime": 7.3836, | |
| "eval_samples_per_second": 8.532, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6234660281352888, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 0.00037468354430379746, | |
| "loss": 0.5053, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "eval_loss": 2.1316659450531006, | |
| "eval_runtime": 7.3635, | |
| "eval_samples_per_second": 8.556, | |
| "eval_steps_per_second": 1.086, | |
| "eval_wer": 0.6303501945525292, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "eval_loss": 2.0722815990448, | |
| "eval_runtime": 7.4257, | |
| "eval_samples_per_second": 8.484, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6255612092187968, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "learning_rate": 0.00037215189873417723, | |
| "loss": 0.5565, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "eval_loss": 2.1390268802642822, | |
| "eval_runtime": 7.3865, | |
| "eval_samples_per_second": 8.529, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6402274768033522, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 0.000369620253164557, | |
| "loss": 0.4819, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "eval_loss": 1.9555976390838623, | |
| "eval_runtime": 7.4506, | |
| "eval_samples_per_second": 8.456, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.6321460640526788, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 18.68, | |
| "learning_rate": 0.0003670886075949367, | |
| "loss": 0.5131, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "eval_loss": 1.9886202812194824, | |
| "eval_runtime": 7.4236, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6333433103861119, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 0.0003645569620253165, | |
| "loss": 0.4798, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "eval_loss": 1.9700343608856201, | |
| "eval_runtime": 7.4038, | |
| "eval_samples_per_second": 8.509, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.625860520802155, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "eval_loss": 1.9770878553390503, | |
| "eval_runtime": 7.3878, | |
| "eval_samples_per_second": 8.528, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6294522598024543, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 0.00036202531645569626, | |
| "loss": 0.5221, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 21.9, | |
| "eval_loss": 1.9879639148712158, | |
| "eval_runtime": 7.4443, | |
| "eval_samples_per_second": 8.463, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6234660281352888, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "learning_rate": 0.000359493670886076, | |
| "loss": 0.4862, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 22.9, | |
| "eval_loss": 2.0993940830230713, | |
| "eval_runtime": 7.4025, | |
| "eval_samples_per_second": 8.511, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.6297515713858126, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 0.0003569620253164557, | |
| "loss": 0.4831, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 23.9, | |
| "eval_loss": 2.0521020889282227, | |
| "eval_runtime": 7.4186, | |
| "eval_samples_per_second": 8.492, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6204729123017061, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "learning_rate": 0.00035443037974683546, | |
| "loss": 0.4952, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "eval_loss": 1.9838017225265503, | |
| "eval_runtime": 7.3891, | |
| "eval_samples_per_second": 8.526, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6064052678838671, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "eval_loss": 2.0318851470947266, | |
| "eval_runtime": 7.3778, | |
| "eval_samples_per_second": 8.539, | |
| "eval_steps_per_second": 1.084, | |
| "eval_wer": 0.6102963184675247, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 26.23, | |
| "learning_rate": 0.00035189873417721524, | |
| "loss": 0.5119, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 26.9, | |
| "eval_loss": 2.041926383972168, | |
| "eval_runtime": 7.4175, | |
| "eval_samples_per_second": 8.493, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.615983238551332, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 0.00034936708860759495, | |
| "loss": 0.4996, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 27.9, | |
| "eval_loss": 2.0072860717773438, | |
| "eval_runtime": 7.4199, | |
| "eval_samples_per_second": 8.491, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6177791080514816, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "learning_rate": 0.00034683544303797467, | |
| "loss": 0.488, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "eval_loss": 2.1739721298217773, | |
| "eval_runtime": 7.4297, | |
| "eval_samples_per_second": 8.479, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6303501945525292, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 29.9, | |
| "learning_rate": 0.00034430379746835444, | |
| "loss": 0.4978, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 29.9, | |
| "eval_loss": 2.2731006145477295, | |
| "eval_runtime": 7.4184, | |
| "eval_samples_per_second": 8.492, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6162825501346902, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 30.9, | |
| "eval_loss": 2.241990804672241, | |
| "eval_runtime": 7.3744, | |
| "eval_samples_per_second": 8.543, | |
| "eval_steps_per_second": 1.085, | |
| "eval_wer": 0.6204729123017061, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 31.23, | |
| "learning_rate": 0.0003417721518987342, | |
| "loss": 0.5259, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 31.9, | |
| "eval_loss": 2.056137800216675, | |
| "eval_runtime": 7.5227, | |
| "eval_samples_per_second": 8.375, | |
| "eval_steps_per_second": 1.063, | |
| "eval_wer": 0.6183777312181982, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 32.45, | |
| "learning_rate": 0.00033924050632911393, | |
| "loss": 0.47, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 32.9, | |
| "eval_loss": 1.9454554319381714, | |
| "eval_runtime": 7.427, | |
| "eval_samples_per_second": 8.483, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6135887458844658, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 33.68, | |
| "learning_rate": 0.0003367088607594937, | |
| "loss": 0.5132, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 33.9, | |
| "eval_loss": 1.9306591749191284, | |
| "eval_runtime": 7.4197, | |
| "eval_samples_per_second": 8.491, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6043100868003591, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 34.9, | |
| "learning_rate": 0.0003341772151898734, | |
| "loss": 0.4972, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 34.9, | |
| "eval_loss": 2.0536110401153564, | |
| "eval_runtime": 7.3867, | |
| "eval_samples_per_second": 8.529, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.612690811134391, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "eval_loss": 1.9113465547561646, | |
| "eval_runtime": 7.4412, | |
| "eval_samples_per_second": 8.466, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6222687818018557, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 36.23, | |
| "learning_rate": 0.0003316455696202532, | |
| "loss": 0.5147, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 36.9, | |
| "eval_loss": 1.9317280054092407, | |
| "eval_runtime": 7.3447, | |
| "eval_samples_per_second": 8.578, | |
| "eval_steps_per_second": 1.089, | |
| "eval_wer": 0.6285543250523795, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 0.00032911392405063296, | |
| "loss": 0.4914, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 37.9, | |
| "eval_loss": 2.1809628009796143, | |
| "eval_runtime": 7.4319, | |
| "eval_samples_per_second": 8.477, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6240646513020054, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "learning_rate": 0.0003265822784810127, | |
| "loss": 0.472, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 38.9, | |
| "eval_loss": 2.1403472423553467, | |
| "eval_runtime": 7.4116, | |
| "eval_samples_per_second": 8.5, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.615983238551332, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 39.9, | |
| "learning_rate": 0.0003240506329113924, | |
| "loss": 0.4825, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 39.9, | |
| "eval_loss": 2.1141297817230225, | |
| "eval_runtime": 7.4006, | |
| "eval_samples_per_second": 8.513, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.6093983837174499, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 40.9, | |
| "eval_loss": 2.2869985103607178, | |
| "eval_runtime": 7.4339, | |
| "eval_samples_per_second": 8.475, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.603112840466926, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 41.23, | |
| "learning_rate": 0.00032151898734177216, | |
| "loss": 0.5138, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 41.9, | |
| "eval_loss": 2.14039945602417, | |
| "eval_runtime": 7.4445, | |
| "eval_samples_per_second": 8.463, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6180784196348399, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "learning_rate": 0.00031898734177215193, | |
| "loss": 0.48, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 42.9, | |
| "eval_loss": 2.024348497390747, | |
| "eval_runtime": 7.3969, | |
| "eval_samples_per_second": 8.517, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.6264591439688716, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 43.68, | |
| "learning_rate": 0.00031645569620253165, | |
| "loss": 0.4598, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 43.9, | |
| "eval_loss": 2.111736297607422, | |
| "eval_runtime": 7.411, | |
| "eval_samples_per_second": 8.501, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.6198742891349895, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 44.9, | |
| "learning_rate": 0.00031392405063291137, | |
| "loss": 0.474, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 44.9, | |
| "eval_loss": 2.0378293991088867, | |
| "eval_runtime": 7.4069, | |
| "eval_samples_per_second": 8.506, | |
| "eval_steps_per_second": 1.08, | |
| "eval_wer": 0.6321460640526788, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 45.9, | |
| "eval_loss": 2.191941261291504, | |
| "eval_runtime": 7.392, | |
| "eval_samples_per_second": 8.523, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.6210715354684226, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 46.23, | |
| "learning_rate": 0.0003113924050632912, | |
| "loss": 0.4933, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 46.9, | |
| "eval_loss": 2.3645358085632324, | |
| "eval_runtime": 7.3897, | |
| "eval_samples_per_second": 8.525, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6108949416342413, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 0.0003088607594936709, | |
| "loss": 0.4692, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 47.9, | |
| "eval_loss": 2.1920251846313477, | |
| "eval_runtime": 7.4249, | |
| "eval_samples_per_second": 8.485, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6076025142173002, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 48.68, | |
| "learning_rate": 0.00030632911392405063, | |
| "loss": 0.4716, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 48.9, | |
| "eval_loss": 2.366262912750244, | |
| "eval_runtime": 7.3885, | |
| "eval_samples_per_second": 8.527, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6034121520502843, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 49.9, | |
| "learning_rate": 0.0003037974683544304, | |
| "loss": 0.4601, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 49.9, | |
| "eval_loss": 2.2838327884674072, | |
| "eval_runtime": 7.4359, | |
| "eval_samples_per_second": 8.472, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.627955701885663, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 50.9, | |
| "eval_loss": 2.0287113189697266, | |
| "eval_runtime": 7.3496, | |
| "eval_samples_per_second": 8.572, | |
| "eval_steps_per_second": 1.088, | |
| "eval_wer": 0.6147859922178989, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 51.23, | |
| "learning_rate": 0.00030126582278481017, | |
| "loss": 0.4891, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 51.9, | |
| "eval_loss": 2.13460636138916, | |
| "eval_runtime": 7.487, | |
| "eval_samples_per_second": 8.415, | |
| "eval_steps_per_second": 1.069, | |
| "eval_wer": 0.6129901227177492, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 52.45, | |
| "learning_rate": 0.0002987341772151899, | |
| "loss": 0.4506, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 52.9, | |
| "eval_loss": 2.155635356903076, | |
| "eval_runtime": 7.4274, | |
| "eval_samples_per_second": 8.482, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6180784196348399, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 53.68, | |
| "learning_rate": 0.0002962025316455696, | |
| "loss": 0.4581, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 53.9, | |
| "eval_loss": 2.0560076236724854, | |
| "eval_runtime": 7.4656, | |
| "eval_samples_per_second": 8.439, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.6228674049685723, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 54.9, | |
| "learning_rate": 0.0002936708860759494, | |
| "loss": 0.4485, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 54.9, | |
| "eval_loss": 1.9943857192993164, | |
| "eval_runtime": 7.4255, | |
| "eval_samples_per_second": 8.484, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.5971266087997605, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 55.9, | |
| "eval_loss": 1.979053020477295, | |
| "eval_runtime": 7.3558, | |
| "eval_samples_per_second": 8.565, | |
| "eval_steps_per_second": 1.088, | |
| "eval_wer": 0.6096976953008082, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 56.23, | |
| "learning_rate": 0.00029113924050632915, | |
| "loss": 0.4942, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 56.9, | |
| "eval_loss": 2.1165554523468018, | |
| "eval_runtime": 7.3957, | |
| "eval_samples_per_second": 8.518, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.6070038910505836, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 57.45, | |
| "learning_rate": 0.00028860759493670886, | |
| "loss": 0.4748, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 57.9, | |
| "eval_loss": 2.027055263519287, | |
| "eval_runtime": 7.413, | |
| "eval_samples_per_second": 8.499, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.6123914995510327, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 58.68, | |
| "learning_rate": 0.00028607594936708863, | |
| "loss": 0.4229, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 58.9, | |
| "eval_loss": 2.0436832904815674, | |
| "eval_runtime": 7.4475, | |
| "eval_samples_per_second": 8.459, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.6228674049685723, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 59.9, | |
| "learning_rate": 0.00028354430379746835, | |
| "loss": 0.45, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 59.9, | |
| "eval_loss": 2.101158618927002, | |
| "eval_runtime": 7.4226, | |
| "eval_samples_per_second": 8.488, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6141873690511823, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 60.9, | |
| "eval_loss": 1.9150625467300415, | |
| "eval_runtime": 7.4336, | |
| "eval_samples_per_second": 8.475, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6049087099670757, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 61.23, | |
| "learning_rate": 0.0002810126582278481, | |
| "loss": 0.4936, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 61.9, | |
| "eval_loss": 1.8990676403045654, | |
| "eval_runtime": 7.475, | |
| "eval_samples_per_second": 8.428, | |
| "eval_steps_per_second": 1.07, | |
| "eval_wer": 0.6046093983837174, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 62.45, | |
| "learning_rate": 0.0002784810126582279, | |
| "loss": 0.4602, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 62.9, | |
| "eval_loss": 1.9813122749328613, | |
| "eval_runtime": 7.4459, | |
| "eval_samples_per_second": 8.461, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.6111942532175996, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 63.68, | |
| "learning_rate": 0.0002759493670886076, | |
| "loss": 0.4626, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 63.9, | |
| "eval_loss": 1.9371625185012817, | |
| "eval_runtime": 7.4834, | |
| "eval_samples_per_second": 8.419, | |
| "eval_steps_per_second": 1.069, | |
| "eval_wer": 0.6135887458844658, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 64.9, | |
| "learning_rate": 0.0002734177215189873, | |
| "loss": 0.445, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 64.9, | |
| "eval_loss": 1.9060248136520386, | |
| "eval_runtime": 7.5103, | |
| "eval_samples_per_second": 8.389, | |
| "eval_steps_per_second": 1.065, | |
| "eval_wer": 0.6153846153846154, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 65.9, | |
| "eval_loss": 1.9573534727096558, | |
| "eval_runtime": 7.3508, | |
| "eval_samples_per_second": 8.571, | |
| "eval_steps_per_second": 1.088, | |
| "eval_wer": 0.6150853038012571, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 66.23, | |
| "learning_rate": 0.0002708860759493671, | |
| "loss": 0.4907, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 66.9, | |
| "eval_loss": 2.094677209854126, | |
| "eval_runtime": 7.4211, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6022149057168512, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 67.45, | |
| "learning_rate": 0.00026835443037974687, | |
| "loss": 0.4723, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 67.9, | |
| "eval_loss": 2.0061404705047607, | |
| "eval_runtime": 7.3728, | |
| "eval_samples_per_second": 8.545, | |
| "eval_steps_per_second": 1.085, | |
| "eval_wer": 0.6010176593834181, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 68.68, | |
| "learning_rate": 0.0002658227848101266, | |
| "loss": 0.4103, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 68.9, | |
| "eval_loss": 1.9557090997695923, | |
| "eval_runtime": 7.4208, | |
| "eval_samples_per_second": 8.49, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6093983837174499, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 69.9, | |
| "learning_rate": 0.0002632911392405063, | |
| "loss": 0.4808, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 69.9, | |
| "eval_loss": 2.1042206287384033, | |
| "eval_runtime": 7.4448, | |
| "eval_samples_per_second": 8.462, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.6087997605507333, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 70.9, | |
| "eval_loss": 2.1360342502593994, | |
| "eval_runtime": 7.4355, | |
| "eval_samples_per_second": 8.473, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6073032026339419, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 71.23, | |
| "learning_rate": 0.00026075949367088613, | |
| "loss": 0.4682, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 71.9, | |
| "eval_loss": 2.128976583480835, | |
| "eval_runtime": 7.3612, | |
| "eval_samples_per_second": 8.558, | |
| "eval_steps_per_second": 1.087, | |
| "eval_wer": 0.6013169709667764, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 72.45, | |
| "learning_rate": 0.00025822784810126584, | |
| "loss": 0.4472, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 72.9, | |
| "eval_loss": 1.9453884363174438, | |
| "eval_runtime": 7.3992, | |
| "eval_samples_per_second": 8.514, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.5989224782999102, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 73.68, | |
| "learning_rate": 0.00025569620253164556, | |
| "loss": 0.4259, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 73.9, | |
| "eval_loss": 2.0936951637268066, | |
| "eval_runtime": 7.4127, | |
| "eval_samples_per_second": 8.499, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.6043100868003591, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 74.9, | |
| "learning_rate": 0.00025316455696202533, | |
| "loss": 0.4464, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 74.9, | |
| "eval_loss": 2.0821897983551025, | |
| "eval_runtime": 7.4228, | |
| "eval_samples_per_second": 8.487, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6058066447171505, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 75.9, | |
| "eval_loss": 2.0128111839294434, | |
| "eval_runtime": 7.4657, | |
| "eval_samples_per_second": 8.439, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.6058066447171505, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 76.23, | |
| "learning_rate": 0.0002506329113924051, | |
| "loss": 0.4775, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 76.9, | |
| "eval_loss": 1.9743807315826416, | |
| "eval_runtime": 7.4326, | |
| "eval_samples_per_second": 8.476, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6093983837174499, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 77.45, | |
| "learning_rate": 0.0002481012658227848, | |
| "loss": 0.4394, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 77.9, | |
| "eval_loss": 1.9991949796676636, | |
| "eval_runtime": 7.4315, | |
| "eval_samples_per_second": 8.477, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.6010176593834181, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 78.68, | |
| "learning_rate": 0.0002455696202531646, | |
| "loss": 0.418, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 78.9, | |
| "eval_loss": 2.169315814971924, | |
| "eval_runtime": 7.4483, | |
| "eval_samples_per_second": 8.458, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.5947321161328943, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 79.9, | |
| "learning_rate": 0.00024303797468354434, | |
| "loss": 0.4384, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 79.9, | |
| "eval_loss": 2.132563829421997, | |
| "eval_runtime": 7.3909, | |
| "eval_samples_per_second": 8.524, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.5923376234660281, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 80.9, | |
| "eval_loss": 2.115138292312622, | |
| "eval_runtime": 7.409, | |
| "eval_samples_per_second": 8.503, | |
| "eval_steps_per_second": 1.08, | |
| "eval_wer": 0.5950314277162526, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 81.23, | |
| "learning_rate": 0.00024050632911392405, | |
| "loss": 0.4971, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 81.9, | |
| "eval_loss": 2.1581170558929443, | |
| "eval_runtime": 7.4413, | |
| "eval_samples_per_second": 8.466, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.5923376234660281, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 82.45, | |
| "learning_rate": 0.0002379746835443038, | |
| "loss": 0.4176, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 82.9, | |
| "eval_loss": 2.087625741958618, | |
| "eval_runtime": 7.4281, | |
| "eval_samples_per_second": 8.481, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6013169709667764, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 83.68, | |
| "learning_rate": 0.00023544303797468357, | |
| "loss": 0.4312, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 83.9, | |
| "eval_loss": 2.1316428184509277, | |
| "eval_runtime": 7.4214, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5935348697994612, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 84.9, | |
| "learning_rate": 0.0002329113924050633, | |
| "loss": 0.4408, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 84.9, | |
| "eval_loss": 2.2627344131469727, | |
| "eval_runtime": 7.4182, | |
| "eval_samples_per_second": 8.493, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5971266087997605, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 85.9, | |
| "eval_loss": 2.279871702194214, | |
| "eval_runtime": 7.385, | |
| "eval_samples_per_second": 8.531, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6111942532175996, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 86.23, | |
| "learning_rate": 0.00023037974683544303, | |
| "loss": 0.4678, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 86.9, | |
| "eval_loss": 2.1239001750946045, | |
| "eval_runtime": 7.4279, | |
| "eval_samples_per_second": 8.482, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.5989224782999102, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 87.45, | |
| "learning_rate": 0.0002278481012658228, | |
| "loss": 0.4288, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 87.9, | |
| "eval_loss": 2.157447576522827, | |
| "eval_runtime": 7.401, | |
| "eval_samples_per_second": 8.512, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.5983238551331936, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 88.68, | |
| "learning_rate": 0.00022531645569620254, | |
| "loss": 0.4157, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 88.9, | |
| "eval_loss": 2.2124781608581543, | |
| "eval_runtime": 7.411, | |
| "eval_samples_per_second": 8.501, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5908410655492368, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 89.9, | |
| "learning_rate": 0.0002227848101265823, | |
| "loss": 0.444, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 89.9, | |
| "eval_loss": 2.054173469543457, | |
| "eval_runtime": 7.3891, | |
| "eval_samples_per_second": 8.526, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.5986231667165519, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 90.9, | |
| "eval_loss": 2.0898985862731934, | |
| "eval_runtime": 7.4515, | |
| "eval_samples_per_second": 8.455, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.5920383118826699, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 91.23, | |
| "learning_rate": 0.00022025316455696206, | |
| "loss": 0.4694, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 91.9, | |
| "eval_loss": 2.11220645904541, | |
| "eval_runtime": 7.3648, | |
| "eval_samples_per_second": 8.554, | |
| "eval_steps_per_second": 1.086, | |
| "eval_wer": 0.6076025142173002, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 92.45, | |
| "learning_rate": 0.00021772151898734177, | |
| "loss": 0.4314, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 92.9, | |
| "eval_loss": 2.0633835792541504, | |
| "eval_runtime": 7.4479, | |
| "eval_samples_per_second": 8.459, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.5950314277162526, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 93.68, | |
| "learning_rate": 0.00021518987341772152, | |
| "loss": 0.4348, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 93.9, | |
| "eval_loss": 2.033348321914673, | |
| "eval_runtime": 7.4247, | |
| "eval_samples_per_second": 8.485, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6046093983837174, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 94.9, | |
| "learning_rate": 0.00021265822784810126, | |
| "loss": 0.4558, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 94.9, | |
| "eval_loss": 2.118844509124756, | |
| "eval_runtime": 7.3971, | |
| "eval_samples_per_second": 8.517, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.5956300508829692, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 95.9, | |
| "eval_loss": 2.060605764389038, | |
| "eval_runtime": 7.4121, | |
| "eval_samples_per_second": 8.5, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5995211014666267, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 96.23, | |
| "learning_rate": 0.00021012658227848103, | |
| "loss": 0.461, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 96.9, | |
| "eval_loss": 2.0599749088287354, | |
| "eval_runtime": 7.378, | |
| "eval_samples_per_second": 8.539, | |
| "eval_steps_per_second": 1.084, | |
| "eval_wer": 0.5971266087997605, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 97.45, | |
| "learning_rate": 0.00020759493670886078, | |
| "loss": 0.4258, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 97.9, | |
| "eval_loss": 2.0478837490081787, | |
| "eval_runtime": 7.4178, | |
| "eval_samples_per_second": 8.493, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.6040107752170009, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 98.68, | |
| "learning_rate": 0.0002050632911392405, | |
| "loss": 0.4395, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 98.9, | |
| "eval_loss": 2.128241539001465, | |
| "eval_runtime": 7.3865, | |
| "eval_samples_per_second": 8.529, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.6055073331337922, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 99.9, | |
| "learning_rate": 0.00020253164556962027, | |
| "loss": 0.4282, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 99.9, | |
| "eval_loss": 2.0592732429504395, | |
| "eval_runtime": 7.4314, | |
| "eval_samples_per_second": 8.478, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6043100868003591, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 100.9, | |
| "eval_loss": 2.0591721534729004, | |
| "eval_runtime": 7.3516, | |
| "eval_samples_per_second": 8.57, | |
| "eval_steps_per_second": 1.088, | |
| "eval_wer": 0.5920383118826699, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 101.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4623, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 101.9, | |
| "eval_loss": 2.0852437019348145, | |
| "eval_runtime": 7.4242, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5944328045495361, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 102.45, | |
| "learning_rate": 0.00019746835443037975, | |
| "loss": 0.4392, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 102.9, | |
| "eval_loss": 2.202364206314087, | |
| "eval_runtime": 7.4726, | |
| "eval_samples_per_second": 8.431, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.5920383118826699, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 103.68, | |
| "learning_rate": 0.0001949367088607595, | |
| "loss": 0.4308, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 103.9, | |
| "eval_loss": 2.178584337234497, | |
| "eval_runtime": 7.4755, | |
| "eval_samples_per_second": 8.427, | |
| "eval_steps_per_second": 1.07, | |
| "eval_wer": 0.5935348697994612, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 104.9, | |
| "learning_rate": 0.00019240506329113924, | |
| "loss": 0.4375, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 104.9, | |
| "eval_loss": 2.108534574508667, | |
| "eval_runtime": 7.495, | |
| "eval_samples_per_second": 8.406, | |
| "eval_steps_per_second": 1.067, | |
| "eval_wer": 0.591140377132595, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 105.9, | |
| "eval_loss": 2.072387218475342, | |
| "eval_runtime": 7.5191, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 1.064, | |
| "eval_wer": 0.5974259203831188, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 106.23, | |
| "learning_rate": 0.00018987341772151899, | |
| "loss": 0.4501, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 106.9, | |
| "eval_loss": 2.13057804107666, | |
| "eval_runtime": 7.3849, | |
| "eval_samples_per_second": 8.531, | |
| "eval_steps_per_second": 1.083, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 107.45, | |
| "learning_rate": 0.00018734177215189873, | |
| "loss": 0.4273, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 107.9, | |
| "eval_loss": 2.134038209915161, | |
| "eval_runtime": 7.4115, | |
| "eval_samples_per_second": 8.5, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5899431307991619, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 108.68, | |
| "learning_rate": 0.0001848101265822785, | |
| "loss": 0.4234, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 108.9, | |
| "eval_loss": 2.1124684810638428, | |
| "eval_runtime": 7.4267, | |
| "eval_samples_per_second": 8.483, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.5980245435498354, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 109.9, | |
| "learning_rate": 0.00018227848101265824, | |
| "loss": 0.4289, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 109.9, | |
| "eval_loss": 2.052570104598999, | |
| "eval_runtime": 7.4264, | |
| "eval_samples_per_second": 8.483, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.6007183478000598, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 110.9, | |
| "eval_loss": 2.095505714416504, | |
| "eval_runtime": 7.4204, | |
| "eval_samples_per_second": 8.49, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5884465728823706, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 111.23, | |
| "learning_rate": 0.000179746835443038, | |
| "loss": 0.478, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 111.9, | |
| "eval_loss": 2.1146061420440674, | |
| "eval_runtime": 7.4324, | |
| "eval_samples_per_second": 8.476, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5872493265489375, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 112.45, | |
| "learning_rate": 0.00017721518987341773, | |
| "loss": 0.4143, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 112.9, | |
| "eval_loss": 2.230980396270752, | |
| "eval_runtime": 7.4614, | |
| "eval_samples_per_second": 8.443, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.5899431307991619, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 113.68, | |
| "learning_rate": 0.00017468354430379748, | |
| "loss": 0.4193, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 113.9, | |
| "eval_loss": 2.2165205478668213, | |
| "eval_runtime": 7.4217, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5899431307991619, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 114.9, | |
| "learning_rate": 0.00017215189873417722, | |
| "loss": 0.4159, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 114.9, | |
| "eval_loss": 2.163135528564453, | |
| "eval_runtime": 7.3968, | |
| "eval_samples_per_second": 8.517, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.5941334929661778, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 115.9, | |
| "eval_loss": 2.1370790004730225, | |
| "eval_runtime": 7.4829, | |
| "eval_samples_per_second": 8.419, | |
| "eval_steps_per_second": 1.069, | |
| "eval_wer": 0.5938341813828195, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 116.23, | |
| "learning_rate": 0.00016962025316455696, | |
| "loss": 0.4776, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 116.9, | |
| "eval_loss": 2.0972321033477783, | |
| "eval_runtime": 7.416, | |
| "eval_samples_per_second": 8.495, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5935348697994612, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 117.45, | |
| "learning_rate": 0.0001670886075949367, | |
| "loss": 0.4143, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 117.9, | |
| "eval_loss": 2.1247801780700684, | |
| "eval_runtime": 7.4939, | |
| "eval_samples_per_second": 8.407, | |
| "eval_steps_per_second": 1.068, | |
| "eval_wer": 0.5917390002993116, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 118.68, | |
| "learning_rate": 0.00016455696202531648, | |
| "loss": 0.4022, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 118.9, | |
| "eval_loss": 2.1317126750946045, | |
| "eval_runtime": 7.4457, | |
| "eval_samples_per_second": 8.461, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.5956300508829692, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 119.9, | |
| "learning_rate": 0.0001620253164556962, | |
| "loss": 0.4346, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 119.9, | |
| "eval_loss": 2.123711347579956, | |
| "eval_runtime": 7.4822, | |
| "eval_samples_per_second": 8.42, | |
| "eval_steps_per_second": 1.069, | |
| "eval_wer": 0.5992217898832685, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 120.9, | |
| "eval_loss": 2.068420648574829, | |
| "eval_runtime": 7.4345, | |
| "eval_samples_per_second": 8.474, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5935348697994612, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 121.23, | |
| "learning_rate": 0.00015949367088607597, | |
| "loss": 0.4564, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 121.9, | |
| "eval_loss": 2.0721840858459473, | |
| "eval_runtime": 7.5192, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 1.064, | |
| "eval_wer": 0.5947321161328943, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 122.45, | |
| "learning_rate": 0.00015696202531645568, | |
| "loss": 0.4243, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 122.9, | |
| "eval_loss": 2.1361429691314697, | |
| "eval_runtime": 7.41, | |
| "eval_samples_per_second": 8.502, | |
| "eval_steps_per_second": 1.08, | |
| "eval_wer": 0.5884465728823706, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 123.68, | |
| "learning_rate": 0.00015443037974683546, | |
| "loss": 0.413, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 123.9, | |
| "eval_loss": 2.120671510696411, | |
| "eval_runtime": 7.446, | |
| "eval_samples_per_second": 8.461, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.5893445076324454, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 124.9, | |
| "learning_rate": 0.0001518987341772152, | |
| "loss": 0.4113, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 124.9, | |
| "eval_loss": 2.0697362422943115, | |
| "eval_runtime": 7.3738, | |
| "eval_samples_per_second": 8.544, | |
| "eval_steps_per_second": 1.085, | |
| "eval_wer": 0.5836575875486382, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 125.9, | |
| "eval_loss": 2.1004655361175537, | |
| "eval_runtime": 7.4731, | |
| "eval_samples_per_second": 8.43, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.5875486381322957, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 126.23, | |
| "learning_rate": 0.00014936708860759494, | |
| "loss": 0.4426, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 126.9, | |
| "eval_loss": 2.082164764404297, | |
| "eval_runtime": 7.3929, | |
| "eval_samples_per_second": 8.522, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.5869500149655792, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 127.45, | |
| "learning_rate": 0.0001468354430379747, | |
| "loss": 0.4255, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 127.9, | |
| "eval_loss": 2.057152032852173, | |
| "eval_runtime": 7.3561, | |
| "eval_samples_per_second": 8.564, | |
| "eval_steps_per_second": 1.088, | |
| "eval_wer": 0.5959293624663274, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 128.68, | |
| "learning_rate": 0.00014430379746835443, | |
| "loss": 0.4214, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 128.9, | |
| "eval_loss": 2.0343050956726074, | |
| "eval_runtime": 7.3751, | |
| "eval_samples_per_second": 8.542, | |
| "eval_steps_per_second": 1.085, | |
| "eval_wer": 0.5935348697994612, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 129.9, | |
| "learning_rate": 0.00014177215189873418, | |
| "loss": 0.4042, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 129.9, | |
| "eval_loss": 2.028167486190796, | |
| "eval_runtime": 7.4579, | |
| "eval_samples_per_second": 8.447, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.5902424423825202, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 130.9, | |
| "eval_loss": 2.0313541889190674, | |
| "eval_runtime": 7.451, | |
| "eval_samples_per_second": 8.455, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.584555522298713, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 131.23, | |
| "learning_rate": 0.00013924050632911395, | |
| "loss": 0.4515, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 131.9, | |
| "eval_loss": 2.0620908737182617, | |
| "eval_runtime": 7.3689, | |
| "eval_samples_per_second": 8.549, | |
| "eval_steps_per_second": 1.086, | |
| "eval_wer": 0.5869500149655792, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 132.45, | |
| "learning_rate": 0.00013670886075949366, | |
| "loss": 0.4138, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 132.9, | |
| "eval_loss": 2.0703771114349365, | |
| "eval_runtime": 7.4244, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5938341813828195, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 133.68, | |
| "learning_rate": 0.00013417721518987343, | |
| "loss": 0.4289, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 133.9, | |
| "eval_loss": 2.0221784114837646, | |
| "eval_runtime": 7.3955, | |
| "eval_samples_per_second": 8.519, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.5896438192158037, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 134.9, | |
| "learning_rate": 0.00013164556962025315, | |
| "loss": 0.3908, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 134.9, | |
| "eval_loss": 2.087918281555176, | |
| "eval_runtime": 7.4644, | |
| "eval_samples_per_second": 8.44, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.5854534570487878, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 135.9, | |
| "eval_loss": 2.1067752838134766, | |
| "eval_runtime": 7.4189, | |
| "eval_samples_per_second": 8.492, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5821610296318468, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 136.23, | |
| "learning_rate": 0.00012911392405063292, | |
| "loss": 0.4489, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 136.9, | |
| "eval_loss": 2.0702497959136963, | |
| "eval_runtime": 7.407, | |
| "eval_samples_per_second": 8.506, | |
| "eval_steps_per_second": 1.08, | |
| "eval_wer": 0.5836575875486382, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 137.45, | |
| "learning_rate": 0.00012658227848101267, | |
| "loss": 0.4191, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 137.9, | |
| "eval_loss": 2.1092591285705566, | |
| "eval_runtime": 7.3713, | |
| "eval_samples_per_second": 8.547, | |
| "eval_steps_per_second": 1.085, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 138.68, | |
| "learning_rate": 0.0001240506329113924, | |
| "loss": 0.4149, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 138.9, | |
| "eval_loss": 2.1046438217163086, | |
| "eval_runtime": 7.4579, | |
| "eval_samples_per_second": 8.447, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.5818617180484885, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 139.9, | |
| "learning_rate": 0.00012151898734177217, | |
| "loss": 0.4127, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 139.9, | |
| "eval_loss": 2.1728851795196533, | |
| "eval_runtime": 7.4678, | |
| "eval_samples_per_second": 8.436, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.5776713558814726, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 140.9, | |
| "eval_loss": 2.163623809814453, | |
| "eval_runtime": 7.3779, | |
| "eval_samples_per_second": 8.539, | |
| "eval_steps_per_second": 1.084, | |
| "eval_wer": 0.5809637832984137, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 141.23, | |
| "learning_rate": 0.0001189873417721519, | |
| "loss": 0.4449, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 141.9, | |
| "eval_loss": 2.1514804363250732, | |
| "eval_runtime": 7.4355, | |
| "eval_samples_per_second": 8.473, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5785692906315475, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 142.45, | |
| "learning_rate": 0.00011645569620253166, | |
| "loss": 0.3977, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 142.9, | |
| "eval_loss": 2.153089761734009, | |
| "eval_runtime": 7.4012, | |
| "eval_samples_per_second": 8.512, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.5773720442981143, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 143.68, | |
| "learning_rate": 0.0001139240506329114, | |
| "loss": 0.4121, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 143.9, | |
| "eval_loss": 2.0857479572296143, | |
| "eval_runtime": 7.4307, | |
| "eval_samples_per_second": 8.478, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.5815624064651302, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 144.9, | |
| "learning_rate": 0.00011139240506329114, | |
| "loss": 0.4363, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 144.9, | |
| "eval_loss": 2.137199878692627, | |
| "eval_runtime": 7.4589, | |
| "eval_samples_per_second": 8.446, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.5821610296318468, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 145.9, | |
| "eval_loss": 2.1901986598968506, | |
| "eval_runtime": 7.401, | |
| "eval_samples_per_second": 8.512, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.5827596527985633, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 146.23, | |
| "learning_rate": 0.00010886075949367089, | |
| "loss": 0.4318, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 146.9, | |
| "eval_loss": 2.1464831829071045, | |
| "eval_runtime": 7.3966, | |
| "eval_samples_per_second": 8.517, | |
| "eval_steps_per_second": 1.082, | |
| "eval_wer": 0.5830589643819216, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 147.45, | |
| "learning_rate": 0.00010632911392405063, | |
| "loss": 0.4112, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 147.9, | |
| "eval_loss": 2.0696558952331543, | |
| "eval_runtime": 7.4385, | |
| "eval_samples_per_second": 8.469, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.5857527686321461, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 148.68, | |
| "learning_rate": 0.00010379746835443039, | |
| "loss": 0.4292, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 148.9, | |
| "eval_loss": 2.084959030151367, | |
| "eval_runtime": 7.5078, | |
| "eval_samples_per_second": 8.391, | |
| "eval_steps_per_second": 1.066, | |
| "eval_wer": 0.5836575875486382, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 149.9, | |
| "learning_rate": 0.00010126582278481013, | |
| "loss": 0.4182, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 149.9, | |
| "eval_loss": 2.1171438694000244, | |
| "eval_runtime": 7.4243, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.584555522298713, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 150.9, | |
| "eval_loss": 2.1019790172576904, | |
| "eval_runtime": 7.4383, | |
| "eval_samples_per_second": 8.47, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5866507033822209, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 151.23, | |
| "learning_rate": 9.873417721518988e-05, | |
| "loss": 0.4381, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 151.9, | |
| "eval_loss": 2.105226516723633, | |
| "eval_runtime": 7.4571, | |
| "eval_samples_per_second": 8.448, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.5848548338820713, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 152.45, | |
| "learning_rate": 9.620253164556962e-05, | |
| "loss": 0.4235, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 152.9, | |
| "eval_loss": 2.1429975032806396, | |
| "eval_runtime": 7.4629, | |
| "eval_samples_per_second": 8.442, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.5863513917988626, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 153.68, | |
| "learning_rate": 9.367088607594936e-05, | |
| "loss": 0.4173, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 153.9, | |
| "eval_loss": 2.1130850315093994, | |
| "eval_runtime": 7.4382, | |
| "eval_samples_per_second": 8.47, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5833582759652799, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 154.9, | |
| "learning_rate": 9.113924050632912e-05, | |
| "loss": 0.3927, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 154.9, | |
| "eval_loss": 2.113377571105957, | |
| "eval_runtime": 7.4677, | |
| "eval_samples_per_second": 8.436, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.584555522298713, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 155.9, | |
| "eval_loss": 2.117252826690674, | |
| "eval_runtime": 7.4474, | |
| "eval_samples_per_second": 8.459, | |
| "eval_steps_per_second": 1.074, | |
| "eval_wer": 0.584555522298713, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 156.23, | |
| "learning_rate": 8.860759493670887e-05, | |
| "loss": 0.4492, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 156.9, | |
| "eval_loss": 2.077221393585205, | |
| "eval_runtime": 7.4748, | |
| "eval_samples_per_second": 8.428, | |
| "eval_steps_per_second": 1.07, | |
| "eval_wer": 0.5800658485483389, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 157.45, | |
| "learning_rate": 8.607594936708861e-05, | |
| "loss": 0.4313, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 157.9, | |
| "eval_loss": 2.030902862548828, | |
| "eval_runtime": 7.3649, | |
| "eval_samples_per_second": 8.554, | |
| "eval_steps_per_second": 1.086, | |
| "eval_wer": 0.5860520802155044, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 158.68, | |
| "learning_rate": 8.354430379746835e-05, | |
| "loss": 0.4015, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 158.9, | |
| "eval_loss": 2.088667154312134, | |
| "eval_runtime": 7.4182, | |
| "eval_samples_per_second": 8.493, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5818617180484885, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 159.9, | |
| "learning_rate": 8.10126582278481e-05, | |
| "loss": 0.4268, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 159.9, | |
| "eval_loss": 2.1811771392822266, | |
| "eval_runtime": 7.3167, | |
| "eval_samples_per_second": 8.61, | |
| "eval_steps_per_second": 1.093, | |
| "eval_wer": 0.5848548338820713, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 160.9, | |
| "eval_loss": 2.1568429470062256, | |
| "eval_runtime": 7.4406, | |
| "eval_samples_per_second": 8.467, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 161.23, | |
| "learning_rate": 7.848101265822784e-05, | |
| "loss": 0.4496, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 161.9, | |
| "eval_loss": 2.080479860305786, | |
| "eval_runtime": 7.4143, | |
| "eval_samples_per_second": 8.497, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5800658485483389, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 162.45, | |
| "learning_rate": 7.59493670886076e-05, | |
| "loss": 0.4121, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 162.9, | |
| "eval_loss": 2.046131134033203, | |
| "eval_runtime": 7.4233, | |
| "eval_samples_per_second": 8.487, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5872493265489375, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 163.68, | |
| "learning_rate": 7.341772151898734e-05, | |
| "loss": 0.401, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 163.9, | |
| "eval_loss": 2.037684202194214, | |
| "eval_runtime": 7.3482, | |
| "eval_samples_per_second": 8.574, | |
| "eval_steps_per_second": 1.089, | |
| "eval_wer": 0.5863513917988626, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 164.9, | |
| "learning_rate": 7.088607594936709e-05, | |
| "loss": 0.4192, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 164.9, | |
| "eval_loss": 2.0183184146881104, | |
| "eval_runtime": 7.3373, | |
| "eval_samples_per_second": 8.586, | |
| "eval_steps_per_second": 1.09, | |
| "eval_wer": 0.5872493265489375, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 165.9, | |
| "eval_loss": 2.0107128620147705, | |
| "eval_runtime": 7.443, | |
| "eval_samples_per_second": 8.464, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.5854534570487878, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 166.23, | |
| "learning_rate": 6.835443037974683e-05, | |
| "loss": 0.4466, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 166.9, | |
| "eval_loss": 2.052823781967163, | |
| "eval_runtime": 7.4214, | |
| "eval_samples_per_second": 8.489, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 167.45, | |
| "learning_rate": 6.582278481012658e-05, | |
| "loss": 0.3981, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 167.9, | |
| "eval_loss": 2.05106258392334, | |
| "eval_runtime": 7.4774, | |
| "eval_samples_per_second": 8.425, | |
| "eval_steps_per_second": 1.07, | |
| "eval_wer": 0.587847949715654, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 168.68, | |
| "learning_rate": 6.329113924050633e-05, | |
| "loss": 0.3967, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 168.9, | |
| "eval_loss": 2.0374269485473633, | |
| "eval_runtime": 7.4229, | |
| "eval_samples_per_second": 8.487, | |
| "eval_steps_per_second": 1.078, | |
| "eval_wer": 0.5866507033822209, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 169.9, | |
| "learning_rate": 6.0759493670886084e-05, | |
| "loss": 0.4072, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 169.9, | |
| "eval_loss": 2.0553550720214844, | |
| "eval_runtime": 7.3678, | |
| "eval_samples_per_second": 8.551, | |
| "eval_steps_per_second": 1.086, | |
| "eval_wer": 0.5866507033822209, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 170.9, | |
| "eval_loss": 2.0388166904449463, | |
| "eval_runtime": 7.4353, | |
| "eval_samples_per_second": 8.473, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5857527686321461, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 171.23, | |
| "learning_rate": 5.822784810126583e-05, | |
| "loss": 0.4581, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 171.9, | |
| "eval_loss": 2.0188472270965576, | |
| "eval_runtime": 7.467, | |
| "eval_samples_per_second": 8.437, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.5914396887159533, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 172.45, | |
| "learning_rate": 5.569620253164557e-05, | |
| "loss": 0.3937, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 172.9, | |
| "eval_loss": 1.9998791217803955, | |
| "eval_runtime": 7.4081, | |
| "eval_samples_per_second": 8.504, | |
| "eval_steps_per_second": 1.08, | |
| "eval_wer": 0.5851541454654295, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 173.68, | |
| "learning_rate": 5.3164556962025316e-05, | |
| "loss": 0.4074, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 173.9, | |
| "eval_loss": 1.9738383293151855, | |
| "eval_runtime": 7.4171, | |
| "eval_samples_per_second": 8.494, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5839568991319964, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 174.9, | |
| "learning_rate": 5.0632911392405066e-05, | |
| "loss": 0.4085, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 174.9, | |
| "eval_loss": 2.009026050567627, | |
| "eval_runtime": 7.412, | |
| "eval_samples_per_second": 8.5, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5842562107153547, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 175.9, | |
| "eval_loss": 1.999009370803833, | |
| "eval_runtime": 7.341, | |
| "eval_samples_per_second": 8.582, | |
| "eval_steps_per_second": 1.09, | |
| "eval_wer": 0.5863513917988626, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 176.23, | |
| "learning_rate": 4.810126582278481e-05, | |
| "loss": 0.4224, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 176.9, | |
| "eval_loss": 2.03910756111145, | |
| "eval_runtime": 7.4284, | |
| "eval_samples_per_second": 8.481, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.5851541454654295, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 177.45, | |
| "learning_rate": 4.556962025316456e-05, | |
| "loss": 0.4471, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 177.9, | |
| "eval_loss": 2.026160955429077, | |
| "eval_runtime": 7.4109, | |
| "eval_samples_per_second": 8.501, | |
| "eval_steps_per_second": 1.079, | |
| "eval_wer": 0.5854534570487878, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 178.68, | |
| "learning_rate": 4.3037974683544305e-05, | |
| "loss": 0.4233, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 178.9, | |
| "eval_loss": 2.0620737075805664, | |
| "eval_runtime": 7.4368, | |
| "eval_samples_per_second": 8.471, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5800658485483389, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 179.9, | |
| "learning_rate": 4.050632911392405e-05, | |
| "loss": 0.409, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 179.9, | |
| "eval_loss": 2.048555612564087, | |
| "eval_runtime": 7.408, | |
| "eval_samples_per_second": 8.504, | |
| "eval_steps_per_second": 1.08, | |
| "eval_wer": 0.584555522298713, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 180.9, | |
| "eval_loss": 2.050809383392334, | |
| "eval_runtime": 7.4021, | |
| "eval_samples_per_second": 8.511, | |
| "eval_steps_per_second": 1.081, | |
| "eval_wer": 0.5806644717150554, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 181.23, | |
| "learning_rate": 3.79746835443038e-05, | |
| "loss": 0.4518, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 181.9, | |
| "eval_loss": 2.024106979370117, | |
| "eval_runtime": 7.3365, | |
| "eval_samples_per_second": 8.587, | |
| "eval_steps_per_second": 1.09, | |
| "eval_wer": 0.5887458844657288, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 182.45, | |
| "learning_rate": 3.5443037974683544e-05, | |
| "loss": 0.4077, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 182.9, | |
| "eval_loss": 2.0168745517730713, | |
| "eval_runtime": 7.4996, | |
| "eval_samples_per_second": 8.4, | |
| "eval_steps_per_second": 1.067, | |
| "eval_wer": 0.5842562107153547, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 183.68, | |
| "learning_rate": 3.291139240506329e-05, | |
| "loss": 0.4197, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 183.9, | |
| "eval_loss": 2.001417636871338, | |
| "eval_runtime": 7.4742, | |
| "eval_samples_per_second": 8.429, | |
| "eval_steps_per_second": 1.07, | |
| "eval_wer": 0.5896438192158037, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 184.9, | |
| "learning_rate": 3.0379746835443042e-05, | |
| "loss": 0.4237, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 184.9, | |
| "eval_loss": 2.018913507461548, | |
| "eval_runtime": 7.5256, | |
| "eval_samples_per_second": 8.371, | |
| "eval_steps_per_second": 1.063, | |
| "eval_wer": 0.5842562107153547, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 185.9, | |
| "eval_loss": 2.0095009803771973, | |
| "eval_runtime": 7.4628, | |
| "eval_samples_per_second": 8.442, | |
| "eval_steps_per_second": 1.072, | |
| "eval_wer": 0.5866507033822209, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 186.23, | |
| "learning_rate": 2.7848101265822786e-05, | |
| "loss": 0.4394, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 186.9, | |
| "eval_loss": 1.9993491172790527, | |
| "eval_runtime": 7.4937, | |
| "eval_samples_per_second": 8.407, | |
| "eval_steps_per_second": 1.068, | |
| "eval_wer": 0.5884465728823706, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 187.45, | |
| "learning_rate": 2.5316455696202533e-05, | |
| "loss": 0.4299, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 187.9, | |
| "eval_loss": 2.009735345840454, | |
| "eval_runtime": 7.4524, | |
| "eval_samples_per_second": 8.454, | |
| "eval_steps_per_second": 1.073, | |
| "eval_wer": 0.5899431307991619, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 188.68, | |
| "learning_rate": 2.278481012658228e-05, | |
| "loss": 0.4198, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 188.9, | |
| "eval_loss": 2.004906177520752, | |
| "eval_runtime": 7.476, | |
| "eval_samples_per_second": 8.427, | |
| "eval_steps_per_second": 1.07, | |
| "eval_wer": 0.5869500149655792, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 189.9, | |
| "learning_rate": 2.0253164556962025e-05, | |
| "loss": 0.4116, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 189.9, | |
| "eval_loss": 1.989935040473938, | |
| "eval_runtime": 7.5052, | |
| "eval_samples_per_second": 8.394, | |
| "eval_steps_per_second": 1.066, | |
| "eval_wer": 0.5875486381322957, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 190.9, | |
| "eval_loss": 1.9814202785491943, | |
| "eval_runtime": 7.5147, | |
| "eval_samples_per_second": 8.384, | |
| "eval_steps_per_second": 1.065, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 1528 | |
| }, | |
| { | |
| "epoch": 191.23, | |
| "learning_rate": 1.7721518987341772e-05, | |
| "loss": 0.445, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 191.9, | |
| "eval_loss": 1.9819977283477783, | |
| "eval_runtime": 7.4909, | |
| "eval_samples_per_second": 8.41, | |
| "eval_steps_per_second": 1.068, | |
| "eval_wer": 0.5887458844657288, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 192.45, | |
| "learning_rate": 1.5189873417721521e-05, | |
| "loss": 0.4198, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 192.9, | |
| "eval_loss": 1.9838072061538696, | |
| "eval_runtime": 7.5105, | |
| "eval_samples_per_second": 8.388, | |
| "eval_steps_per_second": 1.065, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 1544 | |
| }, | |
| { | |
| "epoch": 193.68, | |
| "learning_rate": 1.2658227848101267e-05, | |
| "loss": 0.4065, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 193.9, | |
| "eval_loss": 1.984854817390442, | |
| "eval_runtime": 7.4309, | |
| "eval_samples_per_second": 8.478, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.5884465728823706, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 194.9, | |
| "learning_rate": 1.0126582278481012e-05, | |
| "loss": 0.3917, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 194.9, | |
| "eval_loss": 1.980286717414856, | |
| "eval_runtime": 7.5285, | |
| "eval_samples_per_second": 8.368, | |
| "eval_steps_per_second": 1.063, | |
| "eval_wer": 0.5866507033822209, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 195.9, | |
| "eval_loss": 1.9776644706726074, | |
| "eval_runtime": 7.4846, | |
| "eval_samples_per_second": 8.417, | |
| "eval_steps_per_second": 1.069, | |
| "eval_wer": 0.5881472612990123, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 196.23, | |
| "learning_rate": 7.5949367088607605e-06, | |
| "loss": 0.4239, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 196.9, | |
| "eval_loss": 1.9751547574996948, | |
| "eval_runtime": 7.4451, | |
| "eval_samples_per_second": 8.462, | |
| "eval_steps_per_second": 1.075, | |
| "eval_wer": 0.5875486381322957, | |
| "step": 1576 | |
| }, | |
| { | |
| "epoch": 197.45, | |
| "learning_rate": 5.063291139240506e-06, | |
| "loss": 0.4183, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 197.9, | |
| "eval_loss": 1.9765574932098389, | |
| "eval_runtime": 7.4708, | |
| "eval_samples_per_second": 8.433, | |
| "eval_steps_per_second": 1.071, | |
| "eval_wer": 0.5872493265489375, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 198.68, | |
| "learning_rate": 2.531645569620253e-06, | |
| "loss": 0.3965, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 198.9, | |
| "eval_loss": 1.9772560596466064, | |
| "eval_runtime": 7.4376, | |
| "eval_samples_per_second": 8.471, | |
| "eval_steps_per_second": 1.076, | |
| "eval_wer": 0.5872493265489375, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 199.9, | |
| "learning_rate": 0.0, | |
| "loss": 0.4144, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 199.9, | |
| "eval_loss": 1.9781134128570557, | |
| "eval_runtime": 7.3567, | |
| "eval_samples_per_second": 8.564, | |
| "eval_steps_per_second": 1.087, | |
| "eval_wer": 0.5872493265489375, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 199.9, | |
| "step": 1600, | |
| "total_flos": 1.1848602213269387e+19, | |
| "train_loss": 0.4494818127155304, | |
| "train_runtime": 18323.7781, | |
| "train_samples_per_second": 6.145, | |
| "train_steps_per_second": 0.087 | |
| } | |
| ], | |
| "max_steps": 1600, | |
| "num_train_epochs": 200, | |
| "total_flos": 1.1848602213269387e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |