File size: 25,044 Bytes
9e0bd9b |
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 |
2023-10-06 23:58:06,919 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,920 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): T5LayerNorm()
(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): T5LayerNorm()
(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): T5LayerNorm()
(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): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(final_layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1472, out_features=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-06 23:58:06,920 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,921 MultiCorpus: 1100 train + 206 dev + 240 test sentences
- NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /app/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
2023-10-06 23:58:06,921 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,921 Train: 1100 sentences
2023-10-06 23:58:06,921 (train_with_dev=False, train_with_test=False)
2023-10-06 23:58:06,921 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,921 Training Params:
2023-10-06 23:58:06,921 - learning_rate: "0.00015"
2023-10-06 23:58:06,921 - mini_batch_size: "8"
2023-10-06 23:58:06,921 - max_epochs: "10"
2023-10-06 23:58:06,921 - shuffle: "True"
2023-10-06 23:58:06,921 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,921 Plugins:
2023-10-06 23:58:06,921 - TensorboardLogger
2023-10-06 23:58:06,921 - LinearScheduler | warmup_fraction: '0.1'
2023-10-06 23:58:06,921 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,921 Final evaluation on model from best epoch (best-model.pt)
2023-10-06 23:58:06,921 - metric: "('micro avg', 'f1-score')"
2023-10-06 23:58:06,921 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,922 Computation:
2023-10-06 23:58:06,922 - compute on device: cuda:0
2023-10-06 23:58:06,922 - embedding storage: none
2023-10-06 23:58:06,922 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,922 Model training base path: "hmbench-ajmc/de-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-3"
2023-10-06 23:58:06,922 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,922 ----------------------------------------------------------------------------------------------------
2023-10-06 23:58:06,922 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-06 23:58:15,893 epoch 1 - iter 13/138 - loss 3.20997788 - time (sec): 8.97 - samples/sec: 233.78 - lr: 0.000013 - momentum: 0.000000
2023-10-06 23:58:25,648 epoch 1 - iter 26/138 - loss 3.20472144 - time (sec): 18.73 - samples/sec: 230.97 - lr: 0.000027 - momentum: 0.000000
2023-10-06 23:58:36,233 epoch 1 - iter 39/138 - loss 3.19531578 - time (sec): 29.31 - samples/sec: 227.67 - lr: 0.000041 - momentum: 0.000000
2023-10-06 23:58:46,204 epoch 1 - iter 52/138 - loss 3.18014802 - time (sec): 39.28 - samples/sec: 225.73 - lr: 0.000055 - momentum: 0.000000
2023-10-06 23:58:56,396 epoch 1 - iter 65/138 - loss 3.15473401 - time (sec): 49.47 - samples/sec: 225.56 - lr: 0.000070 - momentum: 0.000000
2023-10-06 23:59:06,168 epoch 1 - iter 78/138 - loss 3.11326509 - time (sec): 59.24 - samples/sec: 224.98 - lr: 0.000084 - momentum: 0.000000
2023-10-06 23:59:15,689 epoch 1 - iter 91/138 - loss 3.05704736 - time (sec): 68.77 - samples/sec: 223.51 - lr: 0.000098 - momentum: 0.000000
2023-10-06 23:59:24,872 epoch 1 - iter 104/138 - loss 2.99443199 - time (sec): 77.95 - samples/sec: 223.03 - lr: 0.000112 - momentum: 0.000000
2023-10-06 23:59:34,511 epoch 1 - iter 117/138 - loss 2.92376879 - time (sec): 87.59 - samples/sec: 223.33 - lr: 0.000126 - momentum: 0.000000
2023-10-06 23:59:43,645 epoch 1 - iter 130/138 - loss 2.85131873 - time (sec): 96.72 - samples/sec: 222.46 - lr: 0.000140 - momentum: 0.000000
2023-10-06 23:59:49,432 ----------------------------------------------------------------------------------------------------
2023-10-06 23:59:49,432 EPOCH 1 done: loss 2.8007 - lr: 0.000140
2023-10-06 23:59:56,007 DEV : loss 1.8414502143859863 - f1-score (micro avg) 0.0
2023-10-06 23:59:56,013 ----------------------------------------------------------------------------------------------------
2023-10-07 00:00:05,813 epoch 2 - iter 13/138 - loss 1.74796308 - time (sec): 9.80 - samples/sec: 234.10 - lr: 0.000149 - momentum: 0.000000
2023-10-07 00:00:15,904 epoch 2 - iter 26/138 - loss 1.69062196 - time (sec): 19.89 - samples/sec: 229.01 - lr: 0.000147 - momentum: 0.000000
2023-10-07 00:00:25,731 epoch 2 - iter 39/138 - loss 1.58228938 - time (sec): 29.72 - samples/sec: 224.52 - lr: 0.000145 - momentum: 0.000000
2023-10-07 00:00:35,837 epoch 2 - iter 52/138 - loss 1.50218282 - time (sec): 39.82 - samples/sec: 225.80 - lr: 0.000144 - momentum: 0.000000
2023-10-07 00:00:45,485 epoch 2 - iter 65/138 - loss 1.43555808 - time (sec): 49.47 - samples/sec: 225.32 - lr: 0.000142 - momentum: 0.000000
2023-10-07 00:00:55,154 epoch 2 - iter 78/138 - loss 1.36493618 - time (sec): 59.14 - samples/sec: 224.58 - lr: 0.000141 - momentum: 0.000000
2023-10-07 00:01:04,473 epoch 2 - iter 91/138 - loss 1.32120162 - time (sec): 68.46 - samples/sec: 223.18 - lr: 0.000139 - momentum: 0.000000
2023-10-07 00:01:13,852 epoch 2 - iter 104/138 - loss 1.28137475 - time (sec): 77.84 - samples/sec: 223.12 - lr: 0.000138 - momentum: 0.000000
2023-10-07 00:01:23,150 epoch 2 - iter 117/138 - loss 1.23997101 - time (sec): 87.14 - samples/sec: 222.41 - lr: 0.000136 - momentum: 0.000000
2023-10-07 00:01:32,727 epoch 2 - iter 130/138 - loss 1.19564686 - time (sec): 96.71 - samples/sec: 222.85 - lr: 0.000134 - momentum: 0.000000
2023-10-07 00:01:38,269 ----------------------------------------------------------------------------------------------------
2023-10-07 00:01:38,269 EPOCH 2 done: loss 1.1702 - lr: 0.000134
2023-10-07 00:01:44,893 DEV : loss 0.8036181926727295 - f1-score (micro avg) 0.0
2023-10-07 00:01:44,898 ----------------------------------------------------------------------------------------------------
2023-10-07 00:01:54,649 epoch 3 - iter 13/138 - loss 0.79601481 - time (sec): 9.75 - samples/sec: 230.08 - lr: 0.000132 - momentum: 0.000000
2023-10-07 00:02:03,917 epoch 3 - iter 26/138 - loss 0.71860922 - time (sec): 19.02 - samples/sec: 226.58 - lr: 0.000130 - momentum: 0.000000
2023-10-07 00:02:14,025 epoch 3 - iter 39/138 - loss 0.67902768 - time (sec): 29.13 - samples/sec: 228.39 - lr: 0.000129 - momentum: 0.000000
2023-10-07 00:02:23,452 epoch 3 - iter 52/138 - loss 0.64466460 - time (sec): 38.55 - samples/sec: 225.52 - lr: 0.000127 - momentum: 0.000000
2023-10-07 00:02:33,711 epoch 3 - iter 65/138 - loss 0.61972971 - time (sec): 48.81 - samples/sec: 226.00 - lr: 0.000126 - momentum: 0.000000
2023-10-07 00:02:43,206 epoch 3 - iter 78/138 - loss 0.60093143 - time (sec): 58.31 - samples/sec: 224.88 - lr: 0.000124 - momentum: 0.000000
2023-10-07 00:02:53,074 epoch 3 - iter 91/138 - loss 0.58832989 - time (sec): 68.17 - samples/sec: 223.59 - lr: 0.000123 - momentum: 0.000000
2023-10-07 00:03:03,492 epoch 3 - iter 104/138 - loss 0.57081164 - time (sec): 78.59 - samples/sec: 225.11 - lr: 0.000121 - momentum: 0.000000
2023-10-07 00:03:12,285 epoch 3 - iter 117/138 - loss 0.55153490 - time (sec): 87.39 - samples/sec: 223.10 - lr: 0.000119 - momentum: 0.000000
2023-10-07 00:03:21,654 epoch 3 - iter 130/138 - loss 0.55009589 - time (sec): 96.75 - samples/sec: 223.33 - lr: 0.000118 - momentum: 0.000000
2023-10-07 00:03:26,998 ----------------------------------------------------------------------------------------------------
2023-10-07 00:03:26,998 EPOCH 3 done: loss 0.5496 - lr: 0.000118
2023-10-07 00:03:33,633 DEV : loss 0.41901326179504395 - f1-score (micro avg) 0.6189
2023-10-07 00:03:33,639 saving best model
2023-10-07 00:03:34,529 ----------------------------------------------------------------------------------------------------
2023-10-07 00:03:44,082 epoch 4 - iter 13/138 - loss 0.47862307 - time (sec): 9.55 - samples/sec: 228.15 - lr: 0.000115 - momentum: 0.000000
2023-10-07 00:03:53,659 epoch 4 - iter 26/138 - loss 0.44598639 - time (sec): 19.13 - samples/sec: 229.40 - lr: 0.000114 - momentum: 0.000000
2023-10-07 00:04:03,615 epoch 4 - iter 39/138 - loss 0.40805908 - time (sec): 29.08 - samples/sec: 226.86 - lr: 0.000112 - momentum: 0.000000
2023-10-07 00:04:12,745 epoch 4 - iter 52/138 - loss 0.39671079 - time (sec): 38.21 - samples/sec: 223.21 - lr: 0.000111 - momentum: 0.000000
2023-10-07 00:04:22,686 epoch 4 - iter 65/138 - loss 0.37971756 - time (sec): 48.16 - samples/sec: 223.51 - lr: 0.000109 - momentum: 0.000000
2023-10-07 00:04:33,000 epoch 4 - iter 78/138 - loss 0.37512928 - time (sec): 58.47 - samples/sec: 225.25 - lr: 0.000107 - momentum: 0.000000
2023-10-07 00:04:42,332 epoch 4 - iter 91/138 - loss 0.36689010 - time (sec): 67.80 - samples/sec: 223.92 - lr: 0.000106 - momentum: 0.000000
2023-10-07 00:04:51,780 epoch 4 - iter 104/138 - loss 0.35327140 - time (sec): 77.25 - samples/sec: 223.11 - lr: 0.000104 - momentum: 0.000000
2023-10-07 00:05:01,251 epoch 4 - iter 117/138 - loss 0.34186476 - time (sec): 86.72 - samples/sec: 221.69 - lr: 0.000103 - momentum: 0.000000
2023-10-07 00:05:10,705 epoch 4 - iter 130/138 - loss 0.33471278 - time (sec): 96.17 - samples/sec: 222.37 - lr: 0.000101 - momentum: 0.000000
2023-10-07 00:05:16,696 ----------------------------------------------------------------------------------------------------
2023-10-07 00:05:16,697 EPOCH 4 done: loss 0.3341 - lr: 0.000101
2023-10-07 00:05:23,337 DEV : loss 0.27274981141090393 - f1-score (micro avg) 0.6831
2023-10-07 00:05:23,343 saving best model
2023-10-07 00:05:24,266 ----------------------------------------------------------------------------------------------------
2023-10-07 00:05:33,970 epoch 5 - iter 13/138 - loss 0.21509147 - time (sec): 9.70 - samples/sec: 214.69 - lr: 0.000099 - momentum: 0.000000
2023-10-07 00:05:43,649 epoch 5 - iter 26/138 - loss 0.23282051 - time (sec): 19.38 - samples/sec: 222.39 - lr: 0.000097 - momentum: 0.000000
2023-10-07 00:05:53,176 epoch 5 - iter 39/138 - loss 0.22838521 - time (sec): 28.91 - samples/sec: 222.12 - lr: 0.000096 - momentum: 0.000000
2023-10-07 00:06:02,488 epoch 5 - iter 52/138 - loss 0.23672214 - time (sec): 38.22 - samples/sec: 220.46 - lr: 0.000094 - momentum: 0.000000
2023-10-07 00:06:12,116 epoch 5 - iter 65/138 - loss 0.23516913 - time (sec): 47.85 - samples/sec: 220.34 - lr: 0.000092 - momentum: 0.000000
2023-10-07 00:06:21,540 epoch 5 - iter 78/138 - loss 0.23287437 - time (sec): 57.27 - samples/sec: 219.06 - lr: 0.000091 - momentum: 0.000000
2023-10-07 00:06:31,810 epoch 5 - iter 91/138 - loss 0.22804770 - time (sec): 67.54 - samples/sec: 221.77 - lr: 0.000089 - momentum: 0.000000
2023-10-07 00:06:41,656 epoch 5 - iter 104/138 - loss 0.22227824 - time (sec): 77.39 - samples/sec: 221.43 - lr: 0.000088 - momentum: 0.000000
2023-10-07 00:06:51,004 epoch 5 - iter 117/138 - loss 0.22083195 - time (sec): 86.74 - samples/sec: 221.42 - lr: 0.000086 - momentum: 0.000000
2023-10-07 00:07:00,641 epoch 5 - iter 130/138 - loss 0.22031519 - time (sec): 96.37 - samples/sec: 221.70 - lr: 0.000085 - momentum: 0.000000
2023-10-07 00:07:06,697 ----------------------------------------------------------------------------------------------------
2023-10-07 00:07:06,697 EPOCH 5 done: loss 0.2182 - lr: 0.000085
2023-10-07 00:07:13,359 DEV : loss 0.19381575286388397 - f1-score (micro avg) 0.7876
2023-10-07 00:07:13,364 saving best model
2023-10-07 00:07:14,290 ----------------------------------------------------------------------------------------------------
2023-10-07 00:07:24,032 epoch 6 - iter 13/138 - loss 0.17702033 - time (sec): 9.74 - samples/sec: 228.83 - lr: 0.000082 - momentum: 0.000000
2023-10-07 00:07:32,974 epoch 6 - iter 26/138 - loss 0.19667121 - time (sec): 18.68 - samples/sec: 224.05 - lr: 0.000080 - momentum: 0.000000
2023-10-07 00:07:42,589 epoch 6 - iter 39/138 - loss 0.18090163 - time (sec): 28.30 - samples/sec: 223.52 - lr: 0.000079 - momentum: 0.000000
2023-10-07 00:07:51,551 epoch 6 - iter 52/138 - loss 0.17305993 - time (sec): 37.26 - samples/sec: 220.13 - lr: 0.000077 - momentum: 0.000000
2023-10-07 00:08:01,459 epoch 6 - iter 65/138 - loss 0.16189015 - time (sec): 47.17 - samples/sec: 220.38 - lr: 0.000076 - momentum: 0.000000
2023-10-07 00:08:11,960 epoch 6 - iter 78/138 - loss 0.16533049 - time (sec): 57.67 - samples/sec: 220.55 - lr: 0.000074 - momentum: 0.000000
2023-10-07 00:08:21,177 epoch 6 - iter 91/138 - loss 0.16497222 - time (sec): 66.89 - samples/sec: 220.18 - lr: 0.000073 - momentum: 0.000000
2023-10-07 00:08:31,048 epoch 6 - iter 104/138 - loss 0.16785639 - time (sec): 76.76 - samples/sec: 220.79 - lr: 0.000071 - momentum: 0.000000
2023-10-07 00:08:41,114 epoch 6 - iter 117/138 - loss 0.16125224 - time (sec): 86.82 - samples/sec: 221.60 - lr: 0.000070 - momentum: 0.000000
2023-10-07 00:08:50,831 epoch 6 - iter 130/138 - loss 0.15620235 - time (sec): 96.54 - samples/sec: 222.86 - lr: 0.000068 - momentum: 0.000000
2023-10-07 00:08:56,555 ----------------------------------------------------------------------------------------------------
2023-10-07 00:08:56,555 EPOCH 6 done: loss 0.1530 - lr: 0.000068
2023-10-07 00:09:03,175 DEV : loss 0.1629297286272049 - f1-score (micro avg) 0.8051
2023-10-07 00:09:03,180 saving best model
2023-10-07 00:09:04,107 ----------------------------------------------------------------------------------------------------
2023-10-07 00:09:12,912 epoch 7 - iter 13/138 - loss 0.13798370 - time (sec): 8.80 - samples/sec: 217.30 - lr: 0.000065 - momentum: 0.000000
2023-10-07 00:09:23,205 epoch 7 - iter 26/138 - loss 0.11167070 - time (sec): 19.10 - samples/sec: 220.67 - lr: 0.000064 - momentum: 0.000000
2023-10-07 00:09:32,951 epoch 7 - iter 39/138 - loss 0.11037866 - time (sec): 28.84 - samples/sec: 224.01 - lr: 0.000062 - momentum: 0.000000
2023-10-07 00:09:42,557 epoch 7 - iter 52/138 - loss 0.10794981 - time (sec): 38.45 - samples/sec: 225.37 - lr: 0.000061 - momentum: 0.000000
2023-10-07 00:09:52,326 epoch 7 - iter 65/138 - loss 0.11452936 - time (sec): 48.22 - samples/sec: 227.03 - lr: 0.000059 - momentum: 0.000000
2023-10-07 00:10:02,256 epoch 7 - iter 78/138 - loss 0.11784007 - time (sec): 58.15 - samples/sec: 228.28 - lr: 0.000058 - momentum: 0.000000
2023-10-07 00:10:11,305 epoch 7 - iter 91/138 - loss 0.11342626 - time (sec): 67.20 - samples/sec: 225.42 - lr: 0.000056 - momentum: 0.000000
2023-10-07 00:10:21,056 epoch 7 - iter 104/138 - loss 0.11570249 - time (sec): 76.95 - samples/sec: 225.10 - lr: 0.000054 - momentum: 0.000000
2023-10-07 00:10:30,445 epoch 7 - iter 117/138 - loss 0.11799732 - time (sec): 86.34 - samples/sec: 224.16 - lr: 0.000053 - momentum: 0.000000
2023-10-07 00:10:40,216 epoch 7 - iter 130/138 - loss 0.11127819 - time (sec): 96.11 - samples/sec: 223.42 - lr: 0.000051 - momentum: 0.000000
2023-10-07 00:10:45,986 ----------------------------------------------------------------------------------------------------
2023-10-07 00:10:45,987 EPOCH 7 done: loss 0.1117 - lr: 0.000051
2023-10-07 00:10:52,599 DEV : loss 0.14532138407230377 - f1-score (micro avg) 0.8392
2023-10-07 00:10:52,604 saving best model
2023-10-07 00:10:53,522 ----------------------------------------------------------------------------------------------------
2023-10-07 00:11:02,630 epoch 8 - iter 13/138 - loss 0.13064244 - time (sec): 9.11 - samples/sec: 224.69 - lr: 0.000049 - momentum: 0.000000
2023-10-07 00:11:12,280 epoch 8 - iter 26/138 - loss 0.10750352 - time (sec): 18.76 - samples/sec: 224.20 - lr: 0.000047 - momentum: 0.000000
2023-10-07 00:11:21,372 epoch 8 - iter 39/138 - loss 0.09435921 - time (sec): 27.85 - samples/sec: 223.50 - lr: 0.000046 - momentum: 0.000000
2023-10-07 00:11:30,587 epoch 8 - iter 52/138 - loss 0.09770834 - time (sec): 37.06 - samples/sec: 223.89 - lr: 0.000044 - momentum: 0.000000
2023-10-07 00:11:40,400 epoch 8 - iter 65/138 - loss 0.09501205 - time (sec): 46.88 - samples/sec: 223.29 - lr: 0.000043 - momentum: 0.000000
2023-10-07 00:11:50,465 epoch 8 - iter 78/138 - loss 0.09375228 - time (sec): 56.94 - samples/sec: 224.74 - lr: 0.000041 - momentum: 0.000000
2023-10-07 00:12:00,390 epoch 8 - iter 91/138 - loss 0.09337249 - time (sec): 66.87 - samples/sec: 224.10 - lr: 0.000039 - momentum: 0.000000
2023-10-07 00:12:11,173 epoch 8 - iter 104/138 - loss 0.09232996 - time (sec): 77.65 - samples/sec: 224.60 - lr: 0.000038 - momentum: 0.000000
2023-10-07 00:12:20,962 epoch 8 - iter 117/138 - loss 0.09141142 - time (sec): 87.44 - samples/sec: 224.66 - lr: 0.000036 - momentum: 0.000000
2023-10-07 00:12:29,593 epoch 8 - iter 130/138 - loss 0.09362675 - time (sec): 96.07 - samples/sec: 223.43 - lr: 0.000035 - momentum: 0.000000
2023-10-07 00:12:35,325 ----------------------------------------------------------------------------------------------------
2023-10-07 00:12:35,325 EPOCH 8 done: loss 0.0911 - lr: 0.000035
2023-10-07 00:12:41,938 DEV : loss 0.13669075071811676 - f1-score (micro avg) 0.8599
2023-10-07 00:12:41,943 saving best model
2023-10-07 00:12:42,843 ----------------------------------------------------------------------------------------------------
2023-10-07 00:12:51,666 epoch 9 - iter 13/138 - loss 0.08601223 - time (sec): 8.82 - samples/sec: 217.19 - lr: 0.000032 - momentum: 0.000000
2023-10-07 00:13:01,354 epoch 9 - iter 26/138 - loss 0.08520771 - time (sec): 18.51 - samples/sec: 223.61 - lr: 0.000031 - momentum: 0.000000
2023-10-07 00:13:10,900 epoch 9 - iter 39/138 - loss 0.09322572 - time (sec): 28.06 - samples/sec: 224.70 - lr: 0.000029 - momentum: 0.000000
2023-10-07 00:13:19,481 epoch 9 - iter 52/138 - loss 0.09083107 - time (sec): 36.64 - samples/sec: 221.50 - lr: 0.000027 - momentum: 0.000000
2023-10-07 00:13:29,106 epoch 9 - iter 65/138 - loss 0.08689703 - time (sec): 46.26 - samples/sec: 222.13 - lr: 0.000026 - momentum: 0.000000
2023-10-07 00:13:39,273 epoch 9 - iter 78/138 - loss 0.08276096 - time (sec): 56.43 - samples/sec: 223.04 - lr: 0.000024 - momentum: 0.000000
2023-10-07 00:13:49,188 epoch 9 - iter 91/138 - loss 0.08174285 - time (sec): 66.34 - samples/sec: 225.01 - lr: 0.000023 - momentum: 0.000000
2023-10-07 00:13:58,803 epoch 9 - iter 104/138 - loss 0.07693049 - time (sec): 75.96 - samples/sec: 225.06 - lr: 0.000021 - momentum: 0.000000
2023-10-07 00:14:08,910 epoch 9 - iter 117/138 - loss 0.07661784 - time (sec): 86.07 - samples/sec: 225.37 - lr: 0.000020 - momentum: 0.000000
2023-10-07 00:14:17,990 epoch 9 - iter 130/138 - loss 0.07746393 - time (sec): 95.15 - samples/sec: 224.71 - lr: 0.000018 - momentum: 0.000000
2023-10-07 00:14:23,877 ----------------------------------------------------------------------------------------------------
2023-10-07 00:14:23,877 EPOCH 9 done: loss 0.0779 - lr: 0.000018
2023-10-07 00:14:30,458 DEV : loss 0.13400736451148987 - f1-score (micro avg) 0.8592
2023-10-07 00:14:30,463 ----------------------------------------------------------------------------------------------------
2023-10-07 00:14:39,776 epoch 10 - iter 13/138 - loss 0.06687981 - time (sec): 9.31 - samples/sec: 218.12 - lr: 0.000016 - momentum: 0.000000
2023-10-07 00:14:49,992 epoch 10 - iter 26/138 - loss 0.06043895 - time (sec): 19.53 - samples/sec: 218.52 - lr: 0.000014 - momentum: 0.000000
2023-10-07 00:14:59,147 epoch 10 - iter 39/138 - loss 0.06901592 - time (sec): 28.68 - samples/sec: 218.70 - lr: 0.000012 - momentum: 0.000000
2023-10-07 00:15:08,154 epoch 10 - iter 52/138 - loss 0.07029173 - time (sec): 37.69 - samples/sec: 218.65 - lr: 0.000011 - momentum: 0.000000
2023-10-07 00:15:17,964 epoch 10 - iter 65/138 - loss 0.07063126 - time (sec): 47.50 - samples/sec: 221.52 - lr: 0.000009 - momentum: 0.000000
2023-10-07 00:15:27,378 epoch 10 - iter 78/138 - loss 0.06996984 - time (sec): 56.91 - samples/sec: 223.08 - lr: 0.000008 - momentum: 0.000000
2023-10-07 00:15:36,413 epoch 10 - iter 91/138 - loss 0.07072405 - time (sec): 65.95 - samples/sec: 222.75 - lr: 0.000006 - momentum: 0.000000
2023-10-07 00:15:46,064 epoch 10 - iter 104/138 - loss 0.07111993 - time (sec): 75.60 - samples/sec: 223.24 - lr: 0.000005 - momentum: 0.000000
2023-10-07 00:15:55,612 epoch 10 - iter 117/138 - loss 0.07174694 - time (sec): 85.15 - samples/sec: 223.59 - lr: 0.000003 - momentum: 0.000000
2023-10-07 00:16:05,752 epoch 10 - iter 130/138 - loss 0.07323074 - time (sec): 95.29 - samples/sec: 225.30 - lr: 0.000001 - momentum: 0.000000
2023-10-07 00:16:11,303 ----------------------------------------------------------------------------------------------------
2023-10-07 00:16:11,303 EPOCH 10 done: loss 0.0722 - lr: 0.000001
2023-10-07 00:16:17,864 DEV : loss 0.13299323618412018 - f1-score (micro avg) 0.8582
2023-10-07 00:16:18,676 ----------------------------------------------------------------------------------------------------
2023-10-07 00:16:18,678 Loading model from best epoch ...
2023-10-07 00:16:21,954 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-07 00:16:29,045
Results:
- F-score (micro) 0.8915
- F-score (macro) 0.5282
- Accuracy 0.8254
By class:
precision recall f1-score support
scope 0.9016 0.9375 0.9192 176
pers 0.9084 0.9297 0.9189 128
work 0.7821 0.8243 0.8026 74
object 0.0000 0.0000 0.0000 2
loc 0.0000 0.0000 0.0000 2
micro avg 0.8801 0.9031 0.8915 382
macro avg 0.5184 0.5383 0.5282 382
weighted avg 0.8713 0.9031 0.8869 382
2023-10-07 00:16:29,045 ----------------------------------------------------------------------------------------------------
|