File size: 22,039 Bytes
a36704b 2fd1fec 7956c2a 6484e0e 07fc669 3ea6b2a c11fe86 8b0bad7 871bd28 c54ad8c 69c7d3e a4cfbca 3c0cb39 f4bcdf6 6829ef1 0666270 de1dbc8 d1dcc67 bae08f8 ac0e8d0 b51d915 13aec20 dce1c5a d166cc2 f8f168e 908dd40 292e265 834516a 69d4dc7 727b745 9a9c11d b8c52bf f99b38b a3e0786 4d57b59 eafb82d 32949ac bf0b012 1df6116 d30d1e5 3e69ec6 9c1d071 9657aa8 5ac507c f8f1b16 bae6071 2ffe7f7 5994ea4 d403897 2972444 2086330 6df9f13 5aaaf67 18a7a50 ff837b7 654547a 344068d c767788 af94b6b 4993684 c5747a3 7ff9db1 7f108b5 9e9ec3b 764d379 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 |
{'loss': 2.4473, 'learning_rate': 8.666666666666667e-05, 'epoch': 0.5}
{'eval_loss': 1.3674653768539429, 'eval_wer': 95.42124542124543, 'eval_runtime': 44.1027, 'eval_samples_per_second': 1.451, 'eval_steps_per_second': 0.045, 'epoch': 0.5}
{'loss': 1.256, 'learning_rate': 2e-05, 'epoch': 1.0}
{'train_runtime': 33.8193, 'train_samples_per_second': 18.924, 'train_steps_per_second': 0.591, 'train_loss': 0.041942973931630455, 'epoch': 1.05}
***** train metrics *****
epoch = 1.05
train_loss = 0.0419
train_runtime = 0:00:33.81
train_samples_per_second = 18.924
train_steps_per_second = 0.591
***** eval metrics *****
epoch = 1.05
eval_loss = 0.9745
eval_runtime = 0:00:20.34
eval_samples = 64
eval_samples_per_second = 3.145
eval_steps_per_second = 0.098
eval_wer = 75.2747
{'loss': 0.9934, 'learning_rate': 7.68421052631579e-05, 'epoch': 0.3}
{'eval_loss': 0.811407208442688, 'eval_wer': 72.16117216117216, 'eval_runtime': 17.9554, 'eval_samples_per_second': 3.564, 'eval_steps_per_second': 0.111, 'epoch': 0.3}
{'loss': 0.9568, 'learning_rate': 6.631578947368421e-05, 'epoch': 0.4}
{'eval_loss': 0.7814445495605469, 'eval_wer': 72.7106227106227, 'eval_runtime': 44.1521, 'eval_samples_per_second': 1.45, 'eval_steps_per_second': 0.045, 'epoch': 0.4}
{'loss': 0.6856, 'learning_rate': 5.5789473684210526e-05, 'epoch': 0.5}
{'eval_loss': 0.7517387866973877, 'eval_wer': 76.92307692307693, 'eval_runtime': 19.7741, 'eval_samples_per_second': 3.237, 'eval_steps_per_second': 0.101, 'epoch': 0.5}
{'loss': 0.7808, 'learning_rate': 4.5263157894736846e-05, 'epoch': 0.6}
{'eval_loss': 0.6514347195625305, 'eval_wer': 63.55311355311355, 'eval_runtime': 19.745, 'eval_samples_per_second': 3.241, 'eval_steps_per_second': 0.101, 'epoch': 0.6}
{'loss': 0.6826, 'learning_rate': 3.473684210526316e-05, 'epoch': 0.7}
{'eval_loss': 0.6197173595428467, 'eval_wer': 60.43956043956044, 'eval_runtime': 19.7014, 'eval_samples_per_second': 3.248, 'eval_steps_per_second': 0.102, 'epoch': 0.7}
{'loss': 0.7832, 'learning_rate': 2.4210526315789474e-05, 'epoch': 0.8}
{'eval_loss': 0.6129069328308105, 'eval_wer': 65.93406593406593, 'eval_runtime': 18.9507, 'eval_samples_per_second': 3.377, 'eval_steps_per_second': 0.106, 'epoch': 0.8}
{'loss': 0.6031, 'learning_rate': 1.3684210526315791e-05, 'epoch': 0.9}
{'eval_loss': 0.5876654982566833, 'eval_wer': 61.35531135531136, 'eval_runtime': 20.4075, 'eval_samples_per_second': 3.136, 'eval_steps_per_second': 0.098, 'epoch': 0.9}
{'loss': 0.6678, 'learning_rate': 3.1578947368421056e-06, 'epoch': 1.0}
{'eval_loss': 0.5758526921272278, 'eval_wer': 61.53846153846154, 'eval_runtime': 19.5593, 'eval_samples_per_second': 3.272, 'eval_steps_per_second': 0.102, 'epoch': 1.0}
{'train_runtime': 782.3972, 'train_samples_per_second': 4.09, 'train_steps_per_second': 0.128, 'train_loss': 0.6153274965286255, 'epoch': 1.0}
***** train metrics *****
epoch = 1.0
train_loss = 0.6153
train_runtime = 0:13:02.39
train_samples_per_second = 4.09
train_steps_per_second = 0.128
***** eval metrics *****
epoch = 1.0
eval_loss = 0.6197
eval_runtime = 0:00:18.63
eval_samples = 64
eval_samples_per_second = 3.435
eval_steps_per_second = 0.107
eval_wer = 60.4396
{'loss': 0.4611, 'learning_rate': 2.96551724137931e-05, 'epoch': 0.07}
{'eval_loss': 0.5625213384628296, 'eval_wer': 57.692307692307686, 'eval_runtime': 19.7626, 'eval_samples_per_second': 3.238, 'eval_steps_per_second': 0.101, 'epoch': 0.07}
{'loss': 0.4451, 'learning_rate': 2.2758620689655175e-05, 'epoch': 0.13}
{'eval_loss': 0.563637375831604, 'eval_wer': 56.59340659340659, 'eval_runtime': 19.0995, 'eval_samples_per_second': 3.351, 'eval_steps_per_second': 0.105, 'epoch': 0.13}
{'loss': 0.3615, 'learning_rate': 1.586206896551724e-05, 'epoch': 0.2}
{'eval_loss': 0.5489554405212402, 'eval_wer': 61.172161172161175, 'eval_runtime': 18.5694, 'eval_samples_per_second': 3.447, 'eval_steps_per_second': 0.108, 'epoch': 0.2}
{'loss': 0.4055, 'learning_rate': 8.96551724137931e-06, 'epoch': 0.27}
{'eval_loss': 0.5382302403450012, 'eval_wer': 55.12820512820513, 'eval_runtime': 22.4274, 'eval_samples_per_second': 2.854, 'eval_steps_per_second': 0.089, 'epoch': 0.27}
{'loss': 0.2946, 'learning_rate': 2.0689655172413796e-06, 'epoch': 0.33}
{'eval_loss': 0.53872150182724, 'eval_wer': 55.67765567765568, 'eval_runtime': 20.4177, 'eval_samples_per_second': 3.135, 'eval_steps_per_second': 0.098, 'epoch': 0.33}
{'train_runtime': 451.4438, 'train_samples_per_second': 10.633, 'train_steps_per_second': 0.332, 'train_loss': 0.13119232177734375, 'epoch': 0.33}
***** train metrics *****
epoch = 0.33
train_loss = 0.1312
train_runtime = 0:07:31.44
train_samples_per_second = 10.633
train_steps_per_second = 0.332
***** eval metrics *****
epoch = 0.33
eval_loss = 0.5382
eval_runtime = 0:00:19.01
eval_samples = 64
eval_samples_per_second = 3.366
eval_steps_per_second = 0.105
eval_wer = 55.1282
{'loss': 0.2716, 'learning_rate': 9.5e-06, 'epoch': 0.05}
{'eval_loss': 0.5364237427711487, 'eval_wer': 54.57875457875458, 'eval_runtime': 16.1176, 'eval_samples_per_second': 3.971, 'eval_steps_per_second': 0.124, 'epoch': 0.05}
{'loss': 0.2765, 'learning_rate': 9.050000000000001e-06, 'epoch': 0.1}
{'eval_loss': 0.5404230952262878, 'eval_wer': 54.761904761904766, 'eval_runtime': 17.8451, 'eval_samples_per_second': 3.586, 'eval_steps_per_second': 0.112, 'epoch': 0.1}
{'loss': 0.2533, 'learning_rate': 8.550000000000001e-06, 'epoch': 0.15}
{'eval_loss': 0.53352290391922, 'eval_wer': 55.12820512820513, 'eval_runtime': 17.1042, 'eval_samples_per_second': 3.742, 'eval_steps_per_second': 0.117, 'epoch': 0.15}
{'loss': 0.3533, 'learning_rate': 8.050000000000001e-06, 'epoch': 0.2}
{'eval_loss': 0.530021071434021, 'eval_wer': 56.59340659340659, 'eval_runtime': 18.1912, 'eval_samples_per_second': 3.518, 'eval_steps_per_second': 0.11, 'epoch': 0.2}
{'loss': 0.2844, 'learning_rate': 7.5500000000000006e-06, 'epoch': 0.25}
{'eval_loss': 0.5341857671737671, 'eval_wer': 55.311355311355314, 'eval_runtime': 17.7172, 'eval_samples_per_second': 3.612, 'eval_steps_per_second': 0.113, 'epoch': 0.25}
{'train_runtime': 406.2172, 'train_samples_per_second': 15.755, 'train_steps_per_second': 0.492, 'train_loss': 0.0719480574131012, 'epoch': 0.25}
***** train metrics *****
epoch = 0.25
train_loss = 0.0719
train_runtime = 0:06:46.21
train_samples_per_second = 15.755
train_steps_per_second = 0.492
***** eval metrics *****
epoch = 0.25
eval_loss = 0.5364
eval_runtime = 0:00:16.60
eval_samples = 64
eval_samples_per_second = 3.853
eval_steps_per_second = 0.12
eval_wer = 54.5788
{'loss': 0.1922, 'learning_rate': 8.033333333333335e-06, 'epoch': 0.03}
{'eval_loss': 0.5239479541778564, 'eval_wer': 55.494505494505496, 'eval_runtime': 16.5572, 'eval_samples_per_second': 3.865, 'eval_steps_per_second': 0.121, 'epoch': 0.03}
{'loss': 0.2229, 'learning_rate': 7.7e-06, 'epoch': 0.07}
{'eval_loss': 0.5312361717224121, 'eval_wer': 54.395604395604394, 'eval_runtime': 17.8694, 'eval_samples_per_second': 3.582, 'eval_steps_per_second': 0.112, 'epoch': 0.07}
{'loss': 0.1976, 'learning_rate': 7.3666666666666676e-06, 'epoch': 0.1}
{'eval_loss': 0.5302589535713196, 'eval_wer': 54.02930402930403, 'eval_runtime': 17.0912, 'eval_samples_per_second': 3.745, 'eval_steps_per_second': 0.117, 'epoch': 0.1}
{'loss': 0.2823, 'learning_rate': 7.033333333333334e-06, 'epoch': 0.13}
{'eval_loss': 0.5269189476966858, 'eval_wer': 54.02930402930403, 'eval_runtime': 17.9989, 'eval_samples_per_second': 3.556, 'eval_steps_per_second': 0.111, 'epoch': 0.13}
{'loss': 0.2265, 'learning_rate': 6.700000000000001e-06, 'epoch': 0.17}
{'eval_loss': 0.5312862992286682, 'eval_wer': 55.67765567765568, 'eval_runtime': 18.4593, 'eval_samples_per_second': 3.467, 'eval_steps_per_second': 0.108, 'epoch': 0.17}
{'loss': 0.3728, 'learning_rate': 6.366666666666668e-06, 'epoch': 0.2}
{'eval_loss': 0.5128015279769897, 'eval_wer': 53.47985347985348, 'eval_runtime': 18.2249, 'eval_samples_per_second': 3.512, 'eval_steps_per_second': 0.11, 'epoch': 0.2}
{'loss': 0.3738, 'learning_rate': 6.033333333333335e-06, 'epoch': 0.23}
{'eval_loss': 0.5025143623352051, 'eval_wer': 52.74725274725275, 'eval_runtime': 17.2543, 'eval_samples_per_second': 3.709, 'eval_steps_per_second': 0.116, 'epoch': 0.23}
{'loss': 0.488, 'learning_rate': 5.7e-06, 'epoch': 0.27}
{'eval_loss': 0.5074095726013184, 'eval_wer': 52.197802197802204, 'eval_runtime': 18.4062, 'eval_samples_per_second': 3.477, 'eval_steps_per_second': 0.109, 'epoch': 0.27}
{'loss': 0.4142, 'learning_rate': 5.366666666666666e-06, 'epoch': 0.3}
{'eval_loss': 0.5057792663574219, 'eval_wer': 52.56410256410257, 'eval_runtime': 16.5894, 'eval_samples_per_second': 3.858, 'eval_steps_per_second': 0.121, 'epoch': 0.3}
{'loss': 0.4407, 'learning_rate': 5.033333333333333e-06, 'epoch': 0.33}
{'eval_loss': 0.5046072602272034, 'eval_wer': 53.11355311355312, 'eval_runtime': 17.9261, 'eval_samples_per_second': 3.57, 'eval_steps_per_second': 0.112, 'epoch': 0.33}
{'train_runtime': 833.6007, 'train_samples_per_second': 11.516, 'train_steps_per_second': 0.36, 'train_loss': 0.10702953418095906, 'epoch': 0.33}
***** train metrics *****
epoch = 0.33
train_loss = 0.107
train_runtime = 0:13:53.60
train_samples_per_second = 11.516
train_steps_per_second = 0.36
***** eval metrics *****
epoch = 0.33
eval_loss = 0.5074
eval_runtime = 0:00:16.82
eval_samples = 64
eval_samples_per_second = 3.804
eval_steps_per_second = 0.119
eval_wer = 52.1978
{'loss': 2.5622, 'learning_rate': 7e-05, 'epoch': 0.1}
{'eval_loss': 1.5401501655578613, 'eval_wer': 94.5054945054945, 'eval_runtime': 62.3188, 'eval_samples_per_second': 1.027, 'eval_steps_per_second': 0.032, 'epoch': 0.1}
{'loss': 1.3719, 'learning_rate': 9.222222222222223e-05, 'epoch': 0.2}
{'eval_loss': 1.001212239265442, 'eval_wer': 75.27472527472527, 'eval_runtime': 18.9902, 'eval_samples_per_second': 3.37, 'eval_steps_per_second': 0.105, 'epoch': 0.2}
{'loss': 0.9898, 'learning_rate': 8.111111111111112e-05, 'epoch': 0.3}
{'eval_loss': 0.8217034339904785, 'eval_wer': 72.7106227106227, 'eval_runtime': 17.7847, 'eval_samples_per_second': 3.599, 'eval_steps_per_second': 0.112, 'epoch': 0.3}
{'loss': 0.9742, 'learning_rate': 7e-05, 'epoch': 0.4}
{'eval_loss': 0.7924289107322693, 'eval_wer': 72.52747252747253, 'eval_runtime': 19.063, 'eval_samples_per_second': 3.357, 'eval_steps_per_second': 0.105, 'epoch': 0.4}
{'loss': 0.6951, 'learning_rate': 5.8888888888888896e-05, 'epoch': 0.5}
{'eval_loss': 0.7628086805343628, 'eval_wer': 76.19047619047619, 'eval_runtime': 17.8327, 'eval_samples_per_second': 3.589, 'eval_steps_per_second': 0.112, 'epoch': 0.5}
{'loss': 0.7824, 'learning_rate': 4.7777777777777784e-05, 'epoch': 0.6}
{'eval_loss': 0.6737741231918335, 'eval_wer': 65.38461538461539, 'eval_runtime': 18.8876, 'eval_samples_per_second': 3.388, 'eval_steps_per_second': 0.106, 'epoch': 0.6}
{'loss': 0.6818, 'learning_rate': 3.6666666666666666e-05, 'epoch': 0.7}
{'eval_loss': 0.6388838291168213, 'eval_wer': 60.07326007326007, 'eval_runtime': 18.9502, 'eval_samples_per_second': 3.377, 'eval_steps_per_second': 0.106, 'epoch': 0.7}
{'loss': 0.7823, 'learning_rate': 2.5555555555555554e-05, 'epoch': 0.8}
{'eval_loss': 0.6208388805389404, 'eval_wer': 65.75091575091575, 'eval_runtime': 18.1881, 'eval_samples_per_second': 3.519, 'eval_steps_per_second': 0.11, 'epoch': 0.8}
{'loss': 0.5994, 'learning_rate': 1.4444444444444444e-05, 'epoch': 0.9}
{'eval_loss': 0.5900620818138123, 'eval_wer': 61.904761904761905, 'eval_runtime': 17.489, 'eval_samples_per_second': 3.659, 'eval_steps_per_second': 0.114, 'epoch': 0.9}
{'loss': 0.6647, 'learning_rate': 3.3333333333333333e-06, 'epoch': 1.0}
{'eval_loss': 0.5789934992790222, 'eval_wer': 61.72161172161172, 'eval_runtime': 18.4962, 'eval_samples_per_second': 3.46, 'eval_steps_per_second': 0.108, 'epoch': 1.0}
{'train_runtime': 873.4716, 'train_samples_per_second': 3.664, 'train_steps_per_second': 0.114, 'train_loss': 1.0103698587417602, 'epoch': 1.0}
***** train metrics *****
epoch = 1.0
train_loss = 1.0104
train_runtime = 0:14:33.47
train_samples_per_second = 3.664
train_steps_per_second = 0.114
***** eval metrics *****
epoch = 1.0
eval_loss = 0.6389
eval_runtime = 0:00:16.85
eval_samples = 64
eval_samples_per_second = 3.798
eval_steps_per_second = 0.119
eval_wer = 60.0733
{'loss': 2.7922, 'learning_rate': 0.0, 'epoch': 0.01}
{'loss': 2.5366, 'learning_rate': 7e-05, 'epoch': 0.05}
{'eval_loss': 1.5401501655578613, 'eval_wer': 94.5054945054945, 'eval_runtime': 61.7756, 'eval_samples_per_second': 1.036, 'eval_steps_per_second': 0.032, 'epoch': 0.05}
{'loss': 1.3721, 'learning_rate': 9.631578947368421e-05, 'epoch': 0.1}
{'eval_loss': 1.0021113157272339, 'eval_wer': 75.82417582417582, 'eval_runtime': 18.2189, 'eval_samples_per_second': 3.513, 'eval_steps_per_second': 0.11, 'epoch': 0.1}
{'loss': 0.9921, 'learning_rate': 9.105263157894738e-05, 'epoch': 0.15}
{'eval_loss': 0.8322427868843079, 'eval_wer': 75.0915750915751, 'eval_runtime': 18.5377, 'eval_samples_per_second': 3.452, 'eval_steps_per_second': 0.108, 'epoch': 0.15}
{'loss': 0.9844, 'learning_rate': 8.578947368421054e-05, 'epoch': 0.2}
{'eval_loss': 0.8080323338508606, 'eval_wer': 72.89377289377289, 'eval_runtime': 18.3811, 'eval_samples_per_second': 3.482, 'eval_steps_per_second': 0.109, 'epoch': 0.2}
{'loss': 0.7071, 'learning_rate': 8.052631578947368e-05, 'epoch': 0.25}
{'eval_loss': 0.7861990332603455, 'eval_wer': 77.2893772893773, 'eval_runtime': 18.6934, 'eval_samples_per_second': 3.424, 'eval_steps_per_second': 0.107, 'epoch': 0.25}
{'loss': 0.7998, 'learning_rate': 7.526315789473685e-05, 'epoch': 0.3}
{'eval_loss': 0.7052078247070312, 'eval_wer': 68.86446886446886, 'eval_runtime': 18.0962, 'eval_samples_per_second': 3.537, 'eval_steps_per_second': 0.111, 'epoch': 0.3}
{'loss': 0.6935, 'learning_rate': 7e-05, 'epoch': 0.35}
{'eval_loss': 0.6780518889427185, 'eval_wer': 64.28571428571429, 'eval_runtime': 18.1288, 'eval_samples_per_second': 3.53, 'eval_steps_per_second': 0.11, 'epoch': 0.35}
{'loss': 0.81, 'learning_rate': 6.473684210526316e-05, 'epoch': 0.4}
{'eval_loss': 0.6341258883476257, 'eval_wer': 63.55311355311355, 'eval_runtime': 17.5354, 'eval_samples_per_second': 3.65, 'eval_steps_per_second': 0.114, 'epoch': 0.4}
{'loss': 0.6133, 'learning_rate': 5.9473684210526315e-05, 'epoch': 0.45}
{'eval_loss': 0.608344316482544, 'eval_wer': 62.637362637362635, 'eval_runtime': 18.2697, 'eval_samples_per_second': 3.503, 'eval_steps_per_second': 0.109, 'epoch': 0.45}
{'loss': 0.6675, 'learning_rate': 5.421052631578948e-05, 'epoch': 0.5}
{'eval_loss': 0.585149347782135, 'eval_wer': 62.82051282051282, 'eval_runtime': 18.1531, 'eval_samples_per_second': 3.526, 'eval_steps_per_second': 0.11, 'epoch': 0.5}
{'loss': 0.5577, 'learning_rate': 4.8947368421052635e-05, 'epoch': 0.55}
{'eval_loss': 0.5650949478149414, 'eval_wer': 59.34065934065934, 'eval_runtime': 18.781, 'eval_samples_per_second': 3.408, 'eval_steps_per_second': 0.106, 'epoch': 0.55}
{'loss': 0.6473, 'learning_rate': 4.368421052631579e-05, 'epoch': 0.6}
{'eval_loss': 0.5637935400009155, 'eval_wer': 58.058608058608066, 'eval_runtime': 19.7936, 'eval_samples_per_second': 3.233, 'eval_steps_per_second': 0.101, 'epoch': 0.6}
{'loss': 0.6018, 'learning_rate': 3.842105263157895e-05, 'epoch': 0.65}
{'eval_loss': 0.5434007048606873, 'eval_wer': 53.84615384615385, 'eval_runtime': 18.5859, 'eval_samples_per_second': 3.443, 'eval_steps_per_second': 0.108, 'epoch': 0.65}
{'loss': 0.5918, 'learning_rate': 3.3157894736842106e-05, 'epoch': 0.7}
{'eval_loss': 0.5384606719017029, 'eval_wer': 54.94505494505495, 'eval_runtime': 17.6361, 'eval_samples_per_second': 3.629, 'eval_steps_per_second': 0.113, 'epoch': 0.7}
{'loss': 0.5654, 'learning_rate': 2.7894736842105263e-05, 'epoch': 0.75}
{'eval_loss': 0.5200322866439819, 'eval_wer': 58.058608058608066, 'eval_runtime': 19.3669, 'eval_samples_per_second': 3.305, 'eval_steps_per_second': 0.103, 'epoch': 0.75}
{'loss': 0.587, 'learning_rate': 2.2631578947368423e-05, 'epoch': 0.8}
{'eval_loss': 0.4974484145641327, 'eval_wer': 57.14285714285714, 'eval_runtime': 20.073, 'eval_samples_per_second': 3.188, 'eval_steps_per_second': 0.1, 'epoch': 0.8}
{'loss': 0.6157, 'learning_rate': 1.736842105263158e-05, 'epoch': 0.85}
{'eval_loss': 0.483424574136734, 'eval_wer': 53.2967032967033, 'eval_runtime': 20.2725, 'eval_samples_per_second': 3.157, 'eval_steps_per_second': 0.099, 'epoch': 0.85}
{'loss': 0.6803, 'learning_rate': 1.2105263157894737e-05, 'epoch': 0.9}
{'eval_loss': 0.4851979613304138, 'eval_wer': 55.86080586080586, 'eval_runtime': 17.9572, 'eval_samples_per_second': 3.564, 'eval_steps_per_second': 0.111, 'epoch': 0.9}
{'loss': 0.4813, 'learning_rate': 6.842105263157896e-06, 'epoch': 0.95}
{'eval_loss': 0.4685819447040558, 'eval_wer': 51.28205128205128, 'eval_runtime': 17.9367, 'eval_samples_per_second': 3.568, 'eval_steps_per_second': 0.112, 'epoch': 0.95}
{'loss': 0.4952, 'learning_rate': 1.5789473684210528e-06, 'epoch': 1.0}
{'eval_loss': 0.4624484181404114, 'eval_wer': 51.46520146520146, 'eval_runtime': 19.165, 'eval_samples_per_second': 3.339, 'eval_steps_per_second': 0.104, 'epoch': 1.0}
{'train_runtime': 2053.4009, 'train_samples_per_second': 3.117, 'train_steps_per_second': 0.097, 'train_loss': 0.8012711083889008, 'epoch': 1.0}
***** train metrics *****
epoch = 1.0
train_loss = 0.8013
train_runtime = 0:34:13.40
train_samples_per_second = 3.117
train_steps_per_second = 0.097
***** eval metrics *****
epoch = 1.0
eval_loss = 0.4686
eval_runtime = 0:00:16.46
eval_samples = 64
eval_samples_per_second = 3.888
eval_steps_per_second = 0.122
eval_wer = 51.2821
{'loss': 0.3956, 'learning_rate': 3.206896551724138e-05, 'epoch': 0.03}
{'eval_loss': 0.46904227137565613, 'eval_wer': 52.01465201465202, 'eval_runtime': 16.6622, 'eval_samples_per_second': 3.841, 'eval_steps_per_second': 0.12, 'epoch': 0.03}
{'loss': 0.3719, 'learning_rate': 2.8620689655172417e-05, 'epoch': 0.07}
{'eval_loss': 0.4673417806625366, 'eval_wer': 52.74725274725275, 'eval_runtime': 17.4548, 'eval_samples_per_second': 3.667, 'eval_steps_per_second': 0.115, 'epoch': 0.07}
{'loss': 0.3168, 'learning_rate': 2.517241379310345e-05, 'epoch': 0.1}
{'eval_loss': 0.44994863867759705, 'eval_wer': 51.46520146520146, 'eval_runtime': 17.0948, 'eval_samples_per_second': 3.744, 'eval_steps_per_second': 0.117, 'epoch': 0.1}
{'loss': 0.3582, 'learning_rate': 2.1724137931034484e-05, 'epoch': 0.13}
{'eval_loss': 0.4524703323841095, 'eval_wer': 46.88644688644688, 'eval_runtime': 17.7891, 'eval_samples_per_second': 3.598, 'eval_steps_per_second': 0.112, 'epoch': 0.13}
{'loss': 0.2475, 'learning_rate': 1.827586206896552e-05, 'epoch': 0.17}
{'eval_loss': 0.46121472120285034, 'eval_wer': 52.38095238095239, 'eval_runtime': 17.7044, 'eval_samples_per_second': 3.615, 'eval_steps_per_second': 0.113, 'epoch': 0.17}
{'loss': 0.2988, 'learning_rate': 1.482758620689655e-05, 'epoch': 0.2}
{'eval_loss': 0.4346223473548889, 'eval_wer': 49.81684981684982, 'eval_runtime': 19.6665, 'eval_samples_per_second': 3.254, 'eval_steps_per_second': 0.102, 'epoch': 0.2}
{'loss': 0.2749, 'learning_rate': 1.1379310344827587e-05, 'epoch': 0.23}
{'eval_loss': 0.42485401034355164, 'eval_wer': 48.9010989010989, 'eval_runtime': 17.6854, 'eval_samples_per_second': 3.619, 'eval_steps_per_second': 0.113, 'epoch': 0.23}
{'loss': 0.3368, 'learning_rate': 7.93103448275862e-06, 'epoch': 0.27}
{'eval_loss': 0.43880951404571533, 'eval_wer': 46.52014652014652, 'eval_runtime': 18.1285, 'eval_samples_per_second': 3.53, 'eval_steps_per_second': 0.11, 'epoch': 0.27}
{'loss': 0.2574, 'learning_rate': 4.482758620689655e-06, 'epoch': 0.3}
{'eval_loss': 0.43085092306137085, 'eval_wer': 46.7032967032967, 'eval_runtime': 18.1023, 'eval_samples_per_second': 3.535, 'eval_steps_per_second': 0.11, 'epoch': 0.3}
{'loss': 0.2921, 'learning_rate': 1.0344827586206898e-06, 'epoch': 0.33}
{'eval_loss': 0.4282010793685913, 'eval_wer': 46.7032967032967, 'eval_runtime': 18.1178, 'eval_samples_per_second': 3.532, 'eval_steps_per_second': 0.11, 'epoch': 0.33}
{'train_runtime': 1208.0467, 'train_samples_per_second': 7.947, 'train_steps_per_second': 0.248, 'train_loss': 0.10500287771224975, 'epoch': 0.33}
***** train metrics *****
epoch = 0.33
train_loss = 0.105
train_runtime = 0:20:08.04
train_samples_per_second = 7.947
train_steps_per_second = 0.248
***** eval metrics *****
epoch = 0.33
eval_loss = 0.4388
eval_runtime = 0:00:16.72
eval_samples = 64
eval_samples_per_second = 3.825
eval_steps_per_second = 0.12
eval_wer = 46.5201
|