File size: 25,243 Bytes
4b9427d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 |
2023-10-11 02:58:49,354 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,356 Model: "SequenceTagger(
(embeddings): ByT5Embeddings(
(model): T5EncoderModel(
(shared): Embedding(384, 1472)
(encoder): T5Stack(
(embed_tokens): Embedding(384, 1472)
(block): ModuleList(
(0): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1472, out_features=384, bias=False)
(k): Linear(in_features=1472, out_features=384, bias=False)
(v): Linear(in_features=1472, out_features=384, bias=False)
(o): Linear(in_features=384, out_features=1472, bias=False)
(relative_attention_bias): Embedding(32, 6)
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseGatedActDense(
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
(wo): Linear(in_features=3584, out_features=1472, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): NewGELUActivation()
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(1-11): 11 x T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1472, out_features=384, bias=False)
(k): Linear(in_features=1472, out_features=384, bias=False)
(v): Linear(in_features=1472, out_features=384, bias=False)
(o): Linear(in_features=384, out_features=1472, bias=False)
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseGatedActDense(
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
(wo): Linear(in_features=3584, out_features=1472, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): NewGELUActivation()
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1472, out_features=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-11 02:58:49,356 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,356 MultiCorpus: 1166 train + 165 dev + 415 test sentences
- NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
2023-10-11 02:58:49,357 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,357 Train: 1166 sentences
2023-10-11 02:58:49,357 (train_with_dev=False, train_with_test=False)
2023-10-11 02:58:49,357 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,357 Training Params:
2023-10-11 02:58:49,357 - learning_rate: "0.00016"
2023-10-11 02:58:49,357 - mini_batch_size: "8"
2023-10-11 02:58:49,357 - max_epochs: "10"
2023-10-11 02:58:49,357 - shuffle: "True"
2023-10-11 02:58:49,357 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,357 Plugins:
2023-10-11 02:58:49,357 - TensorboardLogger
2023-10-11 02:58:49,357 - LinearScheduler | warmup_fraction: '0.1'
2023-10-11 02:58:49,357 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,357 Final evaluation on model from best epoch (best-model.pt)
2023-10-11 02:58:49,357 - metric: "('micro avg', 'f1-score')"
2023-10-11 02:58:49,358 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,358 Computation:
2023-10-11 02:58:49,358 - compute on device: cuda:0
2023-10-11 02:58:49,358 - embedding storage: none
2023-10-11 02:58:49,358 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,358 Model training base path: "hmbench-newseye/fi-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-5"
2023-10-11 02:58:49,358 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,358 ----------------------------------------------------------------------------------------------------
2023-10-11 02:58:49,358 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-11 02:58:58,372 epoch 1 - iter 14/146 - loss 2.82156082 - time (sec): 9.01 - samples/sec: 470.06 - lr: 0.000014 - momentum: 0.000000
2023-10-11 02:59:06,819 epoch 1 - iter 28/146 - loss 2.81328962 - time (sec): 17.46 - samples/sec: 467.31 - lr: 0.000030 - momentum: 0.000000
2023-10-11 02:59:15,404 epoch 1 - iter 42/146 - loss 2.80236709 - time (sec): 26.04 - samples/sec: 455.58 - lr: 0.000045 - momentum: 0.000000
2023-10-11 02:59:25,395 epoch 1 - iter 56/146 - loss 2.77560051 - time (sec): 36.03 - samples/sec: 460.86 - lr: 0.000060 - momentum: 0.000000
2023-10-11 02:59:34,647 epoch 1 - iter 70/146 - loss 2.73504332 - time (sec): 45.29 - samples/sec: 461.08 - lr: 0.000076 - momentum: 0.000000
2023-10-11 02:59:44,395 epoch 1 - iter 84/146 - loss 2.66639699 - time (sec): 55.04 - samples/sec: 469.45 - lr: 0.000091 - momentum: 0.000000
2023-10-11 02:59:53,771 epoch 1 - iter 98/146 - loss 2.58655394 - time (sec): 64.41 - samples/sec: 475.67 - lr: 0.000106 - momentum: 0.000000
2023-10-11 03:00:02,636 epoch 1 - iter 112/146 - loss 2.52547117 - time (sec): 73.28 - samples/sec: 475.66 - lr: 0.000122 - momentum: 0.000000
2023-10-11 03:00:12,006 epoch 1 - iter 126/146 - loss 2.43072282 - time (sec): 82.65 - samples/sec: 478.44 - lr: 0.000137 - momentum: 0.000000
2023-10-11 03:00:20,230 epoch 1 - iter 140/146 - loss 2.35869693 - time (sec): 90.87 - samples/sec: 475.36 - lr: 0.000152 - momentum: 0.000000
2023-10-11 03:00:23,460 ----------------------------------------------------------------------------------------------------
2023-10-11 03:00:23,460 EPOCH 1 done: loss 2.3326 - lr: 0.000152
2023-10-11 03:00:28,956 DEV : loss 1.2650508880615234 - f1-score (micro avg) 0.0
2023-10-11 03:00:28,965 ----------------------------------------------------------------------------------------------------
2023-10-11 03:00:37,834 epoch 2 - iter 14/146 - loss 1.28850784 - time (sec): 8.87 - samples/sec: 483.05 - lr: 0.000158 - momentum: 0.000000
2023-10-11 03:00:46,400 epoch 2 - iter 28/146 - loss 1.17475751 - time (sec): 17.43 - samples/sec: 488.80 - lr: 0.000157 - momentum: 0.000000
2023-10-11 03:00:54,577 epoch 2 - iter 42/146 - loss 1.11252222 - time (sec): 25.61 - samples/sec: 479.42 - lr: 0.000155 - momentum: 0.000000
2023-10-11 03:01:03,357 epoch 2 - iter 56/146 - loss 1.00841290 - time (sec): 34.39 - samples/sec: 481.62 - lr: 0.000153 - momentum: 0.000000
2023-10-11 03:01:12,621 epoch 2 - iter 70/146 - loss 0.99023783 - time (sec): 43.65 - samples/sec: 488.32 - lr: 0.000152 - momentum: 0.000000
2023-10-11 03:01:21,672 epoch 2 - iter 84/146 - loss 0.92269285 - time (sec): 52.71 - samples/sec: 490.27 - lr: 0.000150 - momentum: 0.000000
2023-10-11 03:01:30,342 epoch 2 - iter 98/146 - loss 0.87677537 - time (sec): 61.38 - samples/sec: 490.80 - lr: 0.000148 - momentum: 0.000000
2023-10-11 03:01:38,580 epoch 2 - iter 112/146 - loss 0.83163574 - time (sec): 69.61 - samples/sec: 487.38 - lr: 0.000147 - momentum: 0.000000
2023-10-11 03:01:46,714 epoch 2 - iter 126/146 - loss 0.81335178 - time (sec): 77.75 - samples/sec: 483.21 - lr: 0.000145 - momentum: 0.000000
2023-10-11 03:01:56,170 epoch 2 - iter 140/146 - loss 0.78893900 - time (sec): 87.20 - samples/sec: 486.32 - lr: 0.000143 - momentum: 0.000000
2023-10-11 03:02:00,042 ----------------------------------------------------------------------------------------------------
2023-10-11 03:02:00,043 EPOCH 2 done: loss 0.7803 - lr: 0.000143
2023-10-11 03:02:05,705 DEV : loss 0.4041951894760132 - f1-score (micro avg) 0.0
2023-10-11 03:02:05,714 ----------------------------------------------------------------------------------------------------
2023-10-11 03:02:14,895 epoch 3 - iter 14/146 - loss 0.53427675 - time (sec): 9.18 - samples/sec: 419.66 - lr: 0.000141 - momentum: 0.000000
2023-10-11 03:02:23,336 epoch 3 - iter 28/146 - loss 0.51483169 - time (sec): 17.62 - samples/sec: 439.28 - lr: 0.000139 - momentum: 0.000000
2023-10-11 03:02:32,172 epoch 3 - iter 42/146 - loss 0.48292516 - time (sec): 26.46 - samples/sec: 457.02 - lr: 0.000137 - momentum: 0.000000
2023-10-11 03:02:40,999 epoch 3 - iter 56/146 - loss 0.45342483 - time (sec): 35.28 - samples/sec: 471.31 - lr: 0.000136 - momentum: 0.000000
2023-10-11 03:02:49,374 epoch 3 - iter 70/146 - loss 0.44551814 - time (sec): 43.66 - samples/sec: 471.21 - lr: 0.000134 - momentum: 0.000000
2023-10-11 03:02:57,741 epoch 3 - iter 84/146 - loss 0.42893312 - time (sec): 52.03 - samples/sec: 474.40 - lr: 0.000132 - momentum: 0.000000
2023-10-11 03:03:07,151 epoch 3 - iter 98/146 - loss 0.44060923 - time (sec): 61.43 - samples/sec: 482.77 - lr: 0.000131 - momentum: 0.000000
2023-10-11 03:03:16,212 epoch 3 - iter 112/146 - loss 0.43204748 - time (sec): 70.50 - samples/sec: 472.07 - lr: 0.000129 - momentum: 0.000000
2023-10-11 03:03:26,562 epoch 3 - iter 126/146 - loss 0.42357750 - time (sec): 80.85 - samples/sec: 472.37 - lr: 0.000127 - momentum: 0.000000
2023-10-11 03:03:36,128 epoch 3 - iter 140/146 - loss 0.42216673 - time (sec): 90.41 - samples/sec: 470.41 - lr: 0.000125 - momentum: 0.000000
2023-10-11 03:03:40,267 ----------------------------------------------------------------------------------------------------
2023-10-11 03:03:40,268 EPOCH 3 done: loss 0.4162 - lr: 0.000125
2023-10-11 03:03:45,974 DEV : loss 0.2766019403934479 - f1-score (micro avg) 0.0
2023-10-11 03:03:45,983 ----------------------------------------------------------------------------------------------------
2023-10-11 03:03:56,215 epoch 4 - iter 14/146 - loss 0.28148112 - time (sec): 10.23 - samples/sec: 450.55 - lr: 0.000123 - momentum: 0.000000
2023-10-11 03:04:06,418 epoch 4 - iter 28/146 - loss 0.26087007 - time (sec): 20.43 - samples/sec: 466.80 - lr: 0.000121 - momentum: 0.000000
2023-10-11 03:04:15,473 epoch 4 - iter 42/146 - loss 0.27268962 - time (sec): 29.49 - samples/sec: 473.85 - lr: 0.000120 - momentum: 0.000000
2023-10-11 03:04:24,961 epoch 4 - iter 56/146 - loss 0.32422208 - time (sec): 38.98 - samples/sec: 488.20 - lr: 0.000118 - momentum: 0.000000
2023-10-11 03:04:33,577 epoch 4 - iter 70/146 - loss 0.32316287 - time (sec): 47.59 - samples/sec: 486.47 - lr: 0.000116 - momentum: 0.000000
2023-10-11 03:04:42,328 epoch 4 - iter 84/146 - loss 0.31830554 - time (sec): 56.34 - samples/sec: 483.60 - lr: 0.000115 - momentum: 0.000000
2023-10-11 03:04:50,674 epoch 4 - iter 98/146 - loss 0.32027813 - time (sec): 64.69 - samples/sec: 479.57 - lr: 0.000113 - momentum: 0.000000
2023-10-11 03:04:59,746 epoch 4 - iter 112/146 - loss 0.30992976 - time (sec): 73.76 - samples/sec: 468.27 - lr: 0.000111 - momentum: 0.000000
2023-10-11 03:05:08,557 epoch 4 - iter 126/146 - loss 0.30555368 - time (sec): 82.57 - samples/sec: 469.25 - lr: 0.000109 - momentum: 0.000000
2023-10-11 03:05:17,259 epoch 4 - iter 140/146 - loss 0.30611365 - time (sec): 91.27 - samples/sec: 471.05 - lr: 0.000108 - momentum: 0.000000
2023-10-11 03:05:20,441 ----------------------------------------------------------------------------------------------------
2023-10-11 03:05:20,442 EPOCH 4 done: loss 0.3084 - lr: 0.000108
2023-10-11 03:05:26,153 DEV : loss 0.2286217361688614 - f1-score (micro avg) 0.3883
2023-10-11 03:05:26,162 saving best model
2023-10-11 03:05:27,094 ----------------------------------------------------------------------------------------------------
2023-10-11 03:05:36,127 epoch 5 - iter 14/146 - loss 0.25889454 - time (sec): 9.03 - samples/sec: 470.83 - lr: 0.000105 - momentum: 0.000000
2023-10-11 03:05:46,332 epoch 5 - iter 28/146 - loss 0.23524679 - time (sec): 19.24 - samples/sec: 485.34 - lr: 0.000104 - momentum: 0.000000
2023-10-11 03:05:55,679 epoch 5 - iter 42/146 - loss 0.24651874 - time (sec): 28.58 - samples/sec: 487.14 - lr: 0.000102 - momentum: 0.000000
2023-10-11 03:06:05,138 epoch 5 - iter 56/146 - loss 0.25126634 - time (sec): 38.04 - samples/sec: 487.88 - lr: 0.000100 - momentum: 0.000000
2023-10-11 03:06:14,789 epoch 5 - iter 70/146 - loss 0.27351281 - time (sec): 47.69 - samples/sec: 477.24 - lr: 0.000099 - momentum: 0.000000
2023-10-11 03:06:23,908 epoch 5 - iter 84/146 - loss 0.26826607 - time (sec): 56.81 - samples/sec: 474.74 - lr: 0.000097 - momentum: 0.000000
2023-10-11 03:06:32,783 epoch 5 - iter 98/146 - loss 0.25700981 - time (sec): 65.69 - samples/sec: 472.31 - lr: 0.000095 - momentum: 0.000000
2023-10-11 03:06:40,955 epoch 5 - iter 112/146 - loss 0.25377327 - time (sec): 73.86 - samples/sec: 465.88 - lr: 0.000093 - momentum: 0.000000
2023-10-11 03:06:50,055 epoch 5 - iter 126/146 - loss 0.24593692 - time (sec): 82.96 - samples/sec: 467.80 - lr: 0.000092 - momentum: 0.000000
2023-10-11 03:06:58,949 epoch 5 - iter 140/146 - loss 0.24041901 - time (sec): 91.85 - samples/sec: 467.84 - lr: 0.000090 - momentum: 0.000000
2023-10-11 03:07:02,398 ----------------------------------------------------------------------------------------------------
2023-10-11 03:07:02,398 EPOCH 5 done: loss 0.2400 - lr: 0.000090
2023-10-11 03:07:08,709 DEV : loss 0.1938922256231308 - f1-score (micro avg) 0.5096
2023-10-11 03:07:08,719 saving best model
2023-10-11 03:07:11,341 ----------------------------------------------------------------------------------------------------
2023-10-11 03:07:19,792 epoch 6 - iter 14/146 - loss 0.17003425 - time (sec): 8.45 - samples/sec: 421.76 - lr: 0.000088 - momentum: 0.000000
2023-10-11 03:07:29,419 epoch 6 - iter 28/146 - loss 0.21222092 - time (sec): 18.07 - samples/sec: 424.62 - lr: 0.000086 - momentum: 0.000000
2023-10-11 03:07:38,670 epoch 6 - iter 42/146 - loss 0.21021534 - time (sec): 27.32 - samples/sec: 425.94 - lr: 0.000084 - momentum: 0.000000
2023-10-11 03:07:48,456 epoch 6 - iter 56/146 - loss 0.20003050 - time (sec): 37.11 - samples/sec: 436.31 - lr: 0.000083 - momentum: 0.000000
2023-10-11 03:07:57,208 epoch 6 - iter 70/146 - loss 0.19157871 - time (sec): 45.86 - samples/sec: 443.75 - lr: 0.000081 - momentum: 0.000000
2023-10-11 03:08:06,928 epoch 6 - iter 84/146 - loss 0.17913338 - time (sec): 55.58 - samples/sec: 459.50 - lr: 0.000079 - momentum: 0.000000
2023-10-11 03:08:15,299 epoch 6 - iter 98/146 - loss 0.17940064 - time (sec): 63.95 - samples/sec: 461.31 - lr: 0.000077 - momentum: 0.000000
2023-10-11 03:08:23,678 epoch 6 - iter 112/146 - loss 0.18121308 - time (sec): 72.33 - samples/sec: 463.21 - lr: 0.000076 - momentum: 0.000000
2023-10-11 03:08:31,936 epoch 6 - iter 126/146 - loss 0.17892881 - time (sec): 80.59 - samples/sec: 461.57 - lr: 0.000074 - momentum: 0.000000
2023-10-11 03:08:41,917 epoch 6 - iter 140/146 - loss 0.18585573 - time (sec): 90.57 - samples/sec: 469.98 - lr: 0.000072 - momentum: 0.000000
2023-10-11 03:08:45,984 ----------------------------------------------------------------------------------------------------
2023-10-11 03:08:45,984 EPOCH 6 done: loss 0.1851 - lr: 0.000072
2023-10-11 03:08:51,662 DEV : loss 0.17115506529808044 - f1-score (micro avg) 0.566
2023-10-11 03:08:51,671 saving best model
2023-10-11 03:08:54,392 ----------------------------------------------------------------------------------------------------
2023-10-11 03:09:04,084 epoch 7 - iter 14/146 - loss 0.15701219 - time (sec): 9.69 - samples/sec: 391.69 - lr: 0.000070 - momentum: 0.000000
2023-10-11 03:09:12,536 epoch 7 - iter 28/146 - loss 0.15510761 - time (sec): 18.14 - samples/sec: 423.97 - lr: 0.000068 - momentum: 0.000000
2023-10-11 03:09:20,257 epoch 7 - iter 42/146 - loss 0.14629892 - time (sec): 25.86 - samples/sec: 427.51 - lr: 0.000067 - momentum: 0.000000
2023-10-11 03:09:30,238 epoch 7 - iter 56/146 - loss 0.14700964 - time (sec): 35.84 - samples/sec: 460.86 - lr: 0.000065 - momentum: 0.000000
2023-10-11 03:09:39,544 epoch 7 - iter 70/146 - loss 0.14185422 - time (sec): 45.15 - samples/sec: 455.37 - lr: 0.000063 - momentum: 0.000000
2023-10-11 03:09:48,635 epoch 7 - iter 84/146 - loss 0.14513215 - time (sec): 54.24 - samples/sec: 454.63 - lr: 0.000061 - momentum: 0.000000
2023-10-11 03:09:57,352 epoch 7 - iter 98/146 - loss 0.15171915 - time (sec): 62.96 - samples/sec: 460.05 - lr: 0.000060 - momentum: 0.000000
2023-10-11 03:10:06,611 epoch 7 - iter 112/146 - loss 0.14705100 - time (sec): 72.22 - samples/sec: 460.11 - lr: 0.000058 - momentum: 0.000000
2023-10-11 03:10:15,921 epoch 7 - iter 126/146 - loss 0.14658088 - time (sec): 81.53 - samples/sec: 462.85 - lr: 0.000056 - momentum: 0.000000
2023-10-11 03:10:25,015 epoch 7 - iter 140/146 - loss 0.14531914 - time (sec): 90.62 - samples/sec: 468.17 - lr: 0.000055 - momentum: 0.000000
2023-10-11 03:10:28,779 ----------------------------------------------------------------------------------------------------
2023-10-11 03:10:28,780 EPOCH 7 done: loss 0.1463 - lr: 0.000055
2023-10-11 03:10:34,791 DEV : loss 0.16687284409999847 - f1-score (micro avg) 0.617
2023-10-11 03:10:34,801 saving best model
2023-10-11 03:10:37,399 ----------------------------------------------------------------------------------------------------
2023-10-11 03:10:45,847 epoch 8 - iter 14/146 - loss 0.12928267 - time (sec): 8.44 - samples/sec: 470.41 - lr: 0.000052 - momentum: 0.000000
2023-10-11 03:10:54,199 epoch 8 - iter 28/146 - loss 0.12679178 - time (sec): 16.80 - samples/sec: 486.18 - lr: 0.000051 - momentum: 0.000000
2023-10-11 03:11:02,512 epoch 8 - iter 42/146 - loss 0.15315931 - time (sec): 25.11 - samples/sec: 482.89 - lr: 0.000049 - momentum: 0.000000
2023-10-11 03:11:11,760 epoch 8 - iter 56/146 - loss 0.15510801 - time (sec): 34.36 - samples/sec: 496.46 - lr: 0.000047 - momentum: 0.000000
2023-10-11 03:11:21,747 epoch 8 - iter 70/146 - loss 0.14964513 - time (sec): 44.34 - samples/sec: 479.51 - lr: 0.000045 - momentum: 0.000000
2023-10-11 03:11:30,788 epoch 8 - iter 84/146 - loss 0.14419529 - time (sec): 53.38 - samples/sec: 464.01 - lr: 0.000044 - momentum: 0.000000
2023-10-11 03:11:40,389 epoch 8 - iter 98/146 - loss 0.14165465 - time (sec): 62.99 - samples/sec: 468.01 - lr: 0.000042 - momentum: 0.000000
2023-10-11 03:11:49,920 epoch 8 - iter 112/146 - loss 0.13718145 - time (sec): 72.52 - samples/sec: 473.75 - lr: 0.000040 - momentum: 0.000000
2023-10-11 03:11:58,832 epoch 8 - iter 126/146 - loss 0.13421700 - time (sec): 81.43 - samples/sec: 467.13 - lr: 0.000039 - momentum: 0.000000
2023-10-11 03:12:08,287 epoch 8 - iter 140/146 - loss 0.12891406 - time (sec): 90.88 - samples/sec: 468.80 - lr: 0.000037 - momentum: 0.000000
2023-10-11 03:12:12,150 ----------------------------------------------------------------------------------------------------
2023-10-11 03:12:12,151 EPOCH 8 done: loss 0.1265 - lr: 0.000037
2023-10-11 03:12:17,999 DEV : loss 0.15703192353248596 - f1-score (micro avg) 0.6863
2023-10-11 03:12:18,008 saving best model
2023-10-11 03:12:20,577 ----------------------------------------------------------------------------------------------------
2023-10-11 03:12:29,531 epoch 9 - iter 14/146 - loss 0.10771080 - time (sec): 8.95 - samples/sec: 474.12 - lr: 0.000035 - momentum: 0.000000
2023-10-11 03:12:37,859 epoch 9 - iter 28/146 - loss 0.11279535 - time (sec): 17.28 - samples/sec: 460.24 - lr: 0.000033 - momentum: 0.000000
2023-10-11 03:12:46,480 epoch 9 - iter 42/146 - loss 0.12798759 - time (sec): 25.90 - samples/sec: 467.63 - lr: 0.000031 - momentum: 0.000000
2023-10-11 03:12:54,631 epoch 9 - iter 56/146 - loss 0.13087974 - time (sec): 34.05 - samples/sec: 469.99 - lr: 0.000029 - momentum: 0.000000
2023-10-11 03:13:03,571 epoch 9 - iter 70/146 - loss 0.12721638 - time (sec): 42.99 - samples/sec: 476.40 - lr: 0.000028 - momentum: 0.000000
2023-10-11 03:13:13,313 epoch 9 - iter 84/146 - loss 0.12112059 - time (sec): 52.73 - samples/sec: 482.65 - lr: 0.000026 - momentum: 0.000000
2023-10-11 03:13:21,939 epoch 9 - iter 98/146 - loss 0.11598258 - time (sec): 61.36 - samples/sec: 482.96 - lr: 0.000024 - momentum: 0.000000
2023-10-11 03:13:30,792 epoch 9 - iter 112/146 - loss 0.11367321 - time (sec): 70.21 - samples/sec: 487.31 - lr: 0.000023 - momentum: 0.000000
2023-10-11 03:13:39,412 epoch 9 - iter 126/146 - loss 0.11114356 - time (sec): 78.83 - samples/sec: 491.30 - lr: 0.000021 - momentum: 0.000000
2023-10-11 03:13:48,050 epoch 9 - iter 140/146 - loss 0.11106486 - time (sec): 87.47 - samples/sec: 490.13 - lr: 0.000019 - momentum: 0.000000
2023-10-11 03:13:51,530 ----------------------------------------------------------------------------------------------------
2023-10-11 03:13:51,530 EPOCH 9 done: loss 0.1103 - lr: 0.000019
2023-10-11 03:13:57,096 DEV : loss 0.1517515331506729 - f1-score (micro avg) 0.7064
2023-10-11 03:13:57,105 saving best model
2023-10-11 03:13:59,616 ----------------------------------------------------------------------------------------------------
2023-10-11 03:14:09,366 epoch 10 - iter 14/146 - loss 0.09910516 - time (sec): 9.75 - samples/sec: 425.43 - lr: 0.000017 - momentum: 0.000000
2023-10-11 03:14:18,329 epoch 10 - iter 28/146 - loss 0.11261227 - time (sec): 18.71 - samples/sec: 425.22 - lr: 0.000015 - momentum: 0.000000
2023-10-11 03:14:28,387 epoch 10 - iter 42/146 - loss 0.10216965 - time (sec): 28.77 - samples/sec: 443.50 - lr: 0.000013 - momentum: 0.000000
2023-10-11 03:14:37,707 epoch 10 - iter 56/146 - loss 0.09500174 - time (sec): 38.09 - samples/sec: 450.40 - lr: 0.000012 - momentum: 0.000000
2023-10-11 03:14:46,518 epoch 10 - iter 70/146 - loss 0.09562900 - time (sec): 46.90 - samples/sec: 454.01 - lr: 0.000010 - momentum: 0.000000
2023-10-11 03:14:55,546 epoch 10 - iter 84/146 - loss 0.09501906 - time (sec): 55.93 - samples/sec: 452.85 - lr: 0.000008 - momentum: 0.000000
2023-10-11 03:15:04,659 epoch 10 - iter 98/146 - loss 0.09724605 - time (sec): 65.04 - samples/sec: 457.59 - lr: 0.000007 - momentum: 0.000000
2023-10-11 03:15:15,133 epoch 10 - iter 112/146 - loss 0.10037234 - time (sec): 75.51 - samples/sec: 450.82 - lr: 0.000005 - momentum: 0.000000
2023-10-11 03:15:24,660 epoch 10 - iter 126/146 - loss 0.10048535 - time (sec): 85.04 - samples/sec: 449.83 - lr: 0.000003 - momentum: 0.000000
2023-10-11 03:15:33,705 epoch 10 - iter 140/146 - loss 0.10441213 - time (sec): 94.08 - samples/sec: 450.04 - lr: 0.000002 - momentum: 0.000000
2023-10-11 03:15:37,647 ----------------------------------------------------------------------------------------------------
2023-10-11 03:15:37,647 EPOCH 10 done: loss 0.1026 - lr: 0.000002
2023-10-11 03:15:43,591 DEV : loss 0.14971290528774261 - f1-score (micro avg) 0.7176
2023-10-11 03:15:43,600 saving best model
2023-10-11 03:15:47,074 ----------------------------------------------------------------------------------------------------
2023-10-11 03:15:47,076 Loading model from best epoch ...
2023-10-11 03:15:51,855 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
2023-10-11 03:16:05,085
Results:
- F-score (micro) 0.6815
- F-score (macro) 0.6332
- Accuracy 0.5518
By class:
precision recall f1-score support
PER 0.7686 0.7730 0.7708 348
LOC 0.5942 0.7011 0.6432 261
ORG 0.2763 0.4038 0.3281 52
HumanProd 0.8095 0.7727 0.7907 22
micro avg 0.6490 0.7174 0.6815 683
macro avg 0.6121 0.6627 0.6332 683
weighted avg 0.6658 0.7174 0.6890 683
2023-10-11 03:16:05,086 ----------------------------------------------------------------------------------------------------
|