File size: 25,575 Bytes
ee984ab |
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 |
2023-10-12 01:27:16,208 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,210 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()
)"
2023-10-12 01:27:16,210 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,210 MultiCorpus: 7142 train + 698 dev + 2570 test sentences
- NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator
2023-10-12 01:27:16,210 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,210 Train: 7142 sentences
2023-10-12 01:27:16,211 (train_with_dev=False, train_with_test=False)
2023-10-12 01:27:16,211 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,211 Training Params:
2023-10-12 01:27:16,211 - learning_rate: "0.00016"
2023-10-12 01:27:16,211 - mini_batch_size: "4"
2023-10-12 01:27:16,211 - max_epochs: "10"
2023-10-12 01:27:16,211 - shuffle: "True"
2023-10-12 01:27:16,211 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,211 Plugins:
2023-10-12 01:27:16,211 - TensorboardLogger
2023-10-12 01:27:16,211 - LinearScheduler | warmup_fraction: '0.1'
2023-10-12 01:27:16,211 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,211 Final evaluation on model from best epoch (best-model.pt)
2023-10-12 01:27:16,211 - metric: "('micro avg', 'f1-score')"
2023-10-12 01:27:16,211 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,212 Computation:
2023-10-12 01:27:16,212 - compute on device: cuda:0
2023-10-12 01:27:16,212 - embedding storage: none
2023-10-12 01:27:16,212 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,212 Model training base path: "hmbench-newseye/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-5"
2023-10-12 01:27:16,212 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,212 ----------------------------------------------------------------------------------------------------
2023-10-12 01:27:16,212 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-12 01:28:09,890 epoch 1 - iter 178/1786 - loss 2.80507616 - time (sec): 53.68 - samples/sec: 504.62 - lr: 0.000016 - momentum: 0.000000
2023-10-12 01:29:02,680 epoch 1 - iter 356/1786 - loss 2.63434995 - time (sec): 106.47 - samples/sec: 496.51 - lr: 0.000032 - momentum: 0.000000
2023-10-12 01:29:57,335 epoch 1 - iter 534/1786 - loss 2.33660891 - time (sec): 161.12 - samples/sec: 494.59 - lr: 0.000048 - momentum: 0.000000
2023-10-12 01:30:49,640 epoch 1 - iter 712/1786 - loss 2.05010669 - time (sec): 213.43 - samples/sec: 491.15 - lr: 0.000064 - momentum: 0.000000
2023-10-12 01:31:40,298 epoch 1 - iter 890/1786 - loss 1.79302625 - time (sec): 264.08 - samples/sec: 489.91 - lr: 0.000080 - momentum: 0.000000
2023-10-12 01:32:31,757 epoch 1 - iter 1068/1786 - loss 1.60141163 - time (sec): 315.54 - samples/sec: 484.97 - lr: 0.000096 - momentum: 0.000000
2023-10-12 01:33:23,002 epoch 1 - iter 1246/1786 - loss 1.43923476 - time (sec): 366.79 - samples/sec: 482.67 - lr: 0.000112 - momentum: 0.000000
2023-10-12 01:34:17,377 epoch 1 - iter 1424/1786 - loss 1.31726143 - time (sec): 421.16 - samples/sec: 473.61 - lr: 0.000127 - momentum: 0.000000
2023-10-12 01:35:08,642 epoch 1 - iter 1602/1786 - loss 1.20681398 - time (sec): 472.43 - samples/sec: 473.34 - lr: 0.000143 - momentum: 0.000000
2023-10-12 01:35:58,724 epoch 1 - iter 1780/1786 - loss 1.11235817 - time (sec): 522.51 - samples/sec: 474.81 - lr: 0.000159 - momentum: 0.000000
2023-10-12 01:36:00,213 ----------------------------------------------------------------------------------------------------
2023-10-12 01:36:00,213 EPOCH 1 done: loss 1.1097 - lr: 0.000159
2023-10-12 01:36:18,867 DEV : loss 0.16794759035110474 - f1-score (micro avg) 0.5603
2023-10-12 01:36:18,895 saving best model
2023-10-12 01:36:19,749 ----------------------------------------------------------------------------------------------------
2023-10-12 01:37:09,858 epoch 2 - iter 178/1786 - loss 0.18793256 - time (sec): 50.11 - samples/sec: 498.04 - lr: 0.000158 - momentum: 0.000000
2023-10-12 01:38:01,560 epoch 2 - iter 356/1786 - loss 0.17776196 - time (sec): 101.81 - samples/sec: 494.37 - lr: 0.000156 - momentum: 0.000000
2023-10-12 01:38:56,898 epoch 2 - iter 534/1786 - loss 0.16472447 - time (sec): 157.15 - samples/sec: 479.83 - lr: 0.000155 - momentum: 0.000000
2023-10-12 01:39:48,644 epoch 2 - iter 712/1786 - loss 0.15515345 - time (sec): 208.89 - samples/sec: 477.97 - lr: 0.000153 - momentum: 0.000000
2023-10-12 01:40:41,766 epoch 2 - iter 890/1786 - loss 0.14481166 - time (sec): 262.02 - samples/sec: 481.61 - lr: 0.000151 - momentum: 0.000000
2023-10-12 01:41:32,730 epoch 2 - iter 1068/1786 - loss 0.14070964 - time (sec): 312.98 - samples/sec: 477.58 - lr: 0.000149 - momentum: 0.000000
2023-10-12 01:42:23,528 epoch 2 - iter 1246/1786 - loss 0.13733140 - time (sec): 363.78 - samples/sec: 476.43 - lr: 0.000148 - momentum: 0.000000
2023-10-12 01:43:15,628 epoch 2 - iter 1424/1786 - loss 0.13364336 - time (sec): 415.88 - samples/sec: 477.99 - lr: 0.000146 - momentum: 0.000000
2023-10-12 01:44:06,504 epoch 2 - iter 1602/1786 - loss 0.13125581 - time (sec): 466.75 - samples/sec: 477.55 - lr: 0.000144 - momentum: 0.000000
2023-10-12 01:45:00,109 epoch 2 - iter 1780/1786 - loss 0.12730060 - time (sec): 520.36 - samples/sec: 475.83 - lr: 0.000142 - momentum: 0.000000
2023-10-12 01:45:02,016 ----------------------------------------------------------------------------------------------------
2023-10-12 01:45:02,016 EPOCH 2 done: loss 0.1274 - lr: 0.000142
2023-10-12 01:45:24,922 DEV : loss 0.10730913281440735 - f1-score (micro avg) 0.7623
2023-10-12 01:45:24,958 saving best model
2023-10-12 01:45:28,483 ----------------------------------------------------------------------------------------------------
2023-10-12 01:46:20,438 epoch 3 - iter 178/1786 - loss 0.06605315 - time (sec): 51.95 - samples/sec: 472.43 - lr: 0.000140 - momentum: 0.000000
2023-10-12 01:47:12,817 epoch 3 - iter 356/1786 - loss 0.06559355 - time (sec): 104.33 - samples/sec: 480.15 - lr: 0.000139 - momentum: 0.000000
2023-10-12 01:48:08,733 epoch 3 - iter 534/1786 - loss 0.06577095 - time (sec): 160.24 - samples/sec: 460.10 - lr: 0.000137 - momentum: 0.000000
2023-10-12 01:48:58,726 epoch 3 - iter 712/1786 - loss 0.06735674 - time (sec): 210.24 - samples/sec: 465.58 - lr: 0.000135 - momentum: 0.000000
2023-10-12 01:49:49,932 epoch 3 - iter 890/1786 - loss 0.06649420 - time (sec): 261.44 - samples/sec: 472.92 - lr: 0.000133 - momentum: 0.000000
2023-10-12 01:50:47,225 epoch 3 - iter 1068/1786 - loss 0.06836462 - time (sec): 318.74 - samples/sec: 468.44 - lr: 0.000132 - momentum: 0.000000
2023-10-12 01:51:41,972 epoch 3 - iter 1246/1786 - loss 0.06785363 - time (sec): 373.48 - samples/sec: 466.11 - lr: 0.000130 - momentum: 0.000000
2023-10-12 01:52:37,998 epoch 3 - iter 1424/1786 - loss 0.06934020 - time (sec): 429.51 - samples/sec: 459.33 - lr: 0.000128 - momentum: 0.000000
2023-10-12 01:53:30,221 epoch 3 - iter 1602/1786 - loss 0.07082217 - time (sec): 481.73 - samples/sec: 460.16 - lr: 0.000126 - momentum: 0.000000
2023-10-12 01:54:22,946 epoch 3 - iter 1780/1786 - loss 0.06960424 - time (sec): 534.46 - samples/sec: 463.92 - lr: 0.000125 - momentum: 0.000000
2023-10-12 01:54:24,559 ----------------------------------------------------------------------------------------------------
2023-10-12 01:54:24,559 EPOCH 3 done: loss 0.0697 - lr: 0.000125
2023-10-12 01:54:46,566 DEV : loss 0.12944428622722626 - f1-score (micro avg) 0.7745
2023-10-12 01:54:46,599 saving best model
2023-10-12 01:54:49,221 ----------------------------------------------------------------------------------------------------
2023-10-12 01:55:44,398 epoch 4 - iter 178/1786 - loss 0.05577792 - time (sec): 55.17 - samples/sec: 486.15 - lr: 0.000123 - momentum: 0.000000
2023-10-12 01:56:39,284 epoch 4 - iter 356/1786 - loss 0.05538162 - time (sec): 110.06 - samples/sec: 461.68 - lr: 0.000121 - momentum: 0.000000
2023-10-12 01:57:31,509 epoch 4 - iter 534/1786 - loss 0.05233655 - time (sec): 162.28 - samples/sec: 467.73 - lr: 0.000119 - momentum: 0.000000
2023-10-12 01:58:23,217 epoch 4 - iter 712/1786 - loss 0.05259265 - time (sec): 213.99 - samples/sec: 469.50 - lr: 0.000117 - momentum: 0.000000
2023-10-12 01:59:13,920 epoch 4 - iter 890/1786 - loss 0.05373927 - time (sec): 264.69 - samples/sec: 468.70 - lr: 0.000116 - momentum: 0.000000
2023-10-12 02:00:06,383 epoch 4 - iter 1068/1786 - loss 0.05149636 - time (sec): 317.16 - samples/sec: 470.91 - lr: 0.000114 - momentum: 0.000000
2023-10-12 02:00:58,159 epoch 4 - iter 1246/1786 - loss 0.05173730 - time (sec): 368.93 - samples/sec: 469.30 - lr: 0.000112 - momentum: 0.000000
2023-10-12 02:01:49,397 epoch 4 - iter 1424/1786 - loss 0.05114958 - time (sec): 420.17 - samples/sec: 469.30 - lr: 0.000110 - momentum: 0.000000
2023-10-12 02:02:43,021 epoch 4 - iter 1602/1786 - loss 0.05108851 - time (sec): 473.80 - samples/sec: 472.58 - lr: 0.000109 - momentum: 0.000000
2023-10-12 02:03:34,895 epoch 4 - iter 1780/1786 - loss 0.05115817 - time (sec): 525.67 - samples/sec: 471.96 - lr: 0.000107 - momentum: 0.000000
2023-10-12 02:03:36,495 ----------------------------------------------------------------------------------------------------
2023-10-12 02:03:36,495 EPOCH 4 done: loss 0.0511 - lr: 0.000107
2023-10-12 02:03:56,766 DEV : loss 0.14689753949642181 - f1-score (micro avg) 0.785
2023-10-12 02:03:56,795 saving best model
2023-10-12 02:03:59,385 ----------------------------------------------------------------------------------------------------
2023-10-12 02:04:55,346 epoch 5 - iter 178/1786 - loss 0.03039438 - time (sec): 55.96 - samples/sec: 438.41 - lr: 0.000105 - momentum: 0.000000
2023-10-12 02:05:49,136 epoch 5 - iter 356/1786 - loss 0.03164096 - time (sec): 109.75 - samples/sec: 446.21 - lr: 0.000103 - momentum: 0.000000
2023-10-12 02:06:42,843 epoch 5 - iter 534/1786 - loss 0.03344778 - time (sec): 163.45 - samples/sec: 454.29 - lr: 0.000101 - momentum: 0.000000
2023-10-12 02:07:35,189 epoch 5 - iter 712/1786 - loss 0.03152047 - time (sec): 215.80 - samples/sec: 452.98 - lr: 0.000100 - momentum: 0.000000
2023-10-12 02:08:30,997 epoch 5 - iter 890/1786 - loss 0.03361595 - time (sec): 271.61 - samples/sec: 448.12 - lr: 0.000098 - momentum: 0.000000
2023-10-12 02:09:23,289 epoch 5 - iter 1068/1786 - loss 0.03322299 - time (sec): 323.90 - samples/sec: 451.89 - lr: 0.000096 - momentum: 0.000000
2023-10-12 02:10:20,398 epoch 5 - iter 1246/1786 - loss 0.03402782 - time (sec): 381.01 - samples/sec: 455.72 - lr: 0.000094 - momentum: 0.000000
2023-10-12 02:11:15,612 epoch 5 - iter 1424/1786 - loss 0.03608606 - time (sec): 436.22 - samples/sec: 454.93 - lr: 0.000093 - momentum: 0.000000
2023-10-12 02:12:11,200 epoch 5 - iter 1602/1786 - loss 0.03657160 - time (sec): 491.81 - samples/sec: 453.93 - lr: 0.000091 - momentum: 0.000000
2023-10-12 02:13:08,194 epoch 5 - iter 1780/1786 - loss 0.03671433 - time (sec): 548.80 - samples/sec: 452.08 - lr: 0.000089 - momentum: 0.000000
2023-10-12 02:13:09,930 ----------------------------------------------------------------------------------------------------
2023-10-12 02:13:09,931 EPOCH 5 done: loss 0.0367 - lr: 0.000089
2023-10-12 02:13:31,881 DEV : loss 0.16735321283340454 - f1-score (micro avg) 0.7933
2023-10-12 02:13:31,912 saving best model
2023-10-12 02:13:34,616 ----------------------------------------------------------------------------------------------------
2023-10-12 02:14:29,724 epoch 6 - iter 178/1786 - loss 0.02884951 - time (sec): 55.10 - samples/sec: 466.32 - lr: 0.000087 - momentum: 0.000000
2023-10-12 02:15:24,276 epoch 6 - iter 356/1786 - loss 0.02844827 - time (sec): 109.66 - samples/sec: 454.00 - lr: 0.000085 - momentum: 0.000000
2023-10-12 02:16:22,180 epoch 6 - iter 534/1786 - loss 0.02788463 - time (sec): 167.56 - samples/sec: 460.39 - lr: 0.000084 - momentum: 0.000000
2023-10-12 02:17:16,497 epoch 6 - iter 712/1786 - loss 0.02904160 - time (sec): 221.88 - samples/sec: 456.66 - lr: 0.000082 - momentum: 0.000000
2023-10-12 02:18:11,328 epoch 6 - iter 890/1786 - loss 0.02995947 - time (sec): 276.71 - samples/sec: 460.24 - lr: 0.000080 - momentum: 0.000000
2023-10-12 02:19:04,986 epoch 6 - iter 1068/1786 - loss 0.02837177 - time (sec): 330.37 - samples/sec: 459.17 - lr: 0.000078 - momentum: 0.000000
2023-10-12 02:19:57,466 epoch 6 - iter 1246/1786 - loss 0.02758746 - time (sec): 382.85 - samples/sec: 459.16 - lr: 0.000077 - momentum: 0.000000
2023-10-12 02:20:51,594 epoch 6 - iter 1424/1786 - loss 0.02731558 - time (sec): 436.97 - samples/sec: 459.85 - lr: 0.000075 - momentum: 0.000000
2023-10-12 02:21:44,296 epoch 6 - iter 1602/1786 - loss 0.02738174 - time (sec): 489.68 - samples/sec: 457.93 - lr: 0.000073 - momentum: 0.000000
2023-10-12 02:22:38,466 epoch 6 - iter 1780/1786 - loss 0.02826862 - time (sec): 543.85 - samples/sec: 455.42 - lr: 0.000071 - momentum: 0.000000
2023-10-12 02:22:40,335 ----------------------------------------------------------------------------------------------------
2023-10-12 02:22:40,335 EPOCH 6 done: loss 0.0282 - lr: 0.000071
2023-10-12 02:23:01,339 DEV : loss 0.1834934949874878 - f1-score (micro avg) 0.7908
2023-10-12 02:23:01,368 ----------------------------------------------------------------------------------------------------
2023-10-12 02:23:53,130 epoch 7 - iter 178/1786 - loss 0.02428625 - time (sec): 51.76 - samples/sec: 464.99 - lr: 0.000069 - momentum: 0.000000
2023-10-12 02:24:46,191 epoch 7 - iter 356/1786 - loss 0.01938786 - time (sec): 104.82 - samples/sec: 475.11 - lr: 0.000068 - momentum: 0.000000
2023-10-12 02:25:37,985 epoch 7 - iter 534/1786 - loss 0.01994075 - time (sec): 156.62 - samples/sec: 470.15 - lr: 0.000066 - momentum: 0.000000
2023-10-12 02:26:35,234 epoch 7 - iter 712/1786 - loss 0.01883127 - time (sec): 213.86 - samples/sec: 465.13 - lr: 0.000064 - momentum: 0.000000
2023-10-12 02:27:29,734 epoch 7 - iter 890/1786 - loss 0.02000040 - time (sec): 268.36 - samples/sec: 463.92 - lr: 0.000062 - momentum: 0.000000
2023-10-12 02:28:24,145 epoch 7 - iter 1068/1786 - loss 0.01988337 - time (sec): 322.78 - samples/sec: 462.58 - lr: 0.000061 - momentum: 0.000000
2023-10-12 02:29:21,554 epoch 7 - iter 1246/1786 - loss 0.01983623 - time (sec): 380.18 - samples/sec: 456.64 - lr: 0.000059 - momentum: 0.000000
2023-10-12 02:30:17,602 epoch 7 - iter 1424/1786 - loss 0.02013644 - time (sec): 436.23 - samples/sec: 453.81 - lr: 0.000057 - momentum: 0.000000
2023-10-12 02:31:11,178 epoch 7 - iter 1602/1786 - loss 0.02053497 - time (sec): 489.81 - samples/sec: 455.80 - lr: 0.000055 - momentum: 0.000000
2023-10-12 02:32:06,509 epoch 7 - iter 1780/1786 - loss 0.02060644 - time (sec): 545.14 - samples/sec: 454.69 - lr: 0.000053 - momentum: 0.000000
2023-10-12 02:32:08,217 ----------------------------------------------------------------------------------------------------
2023-10-12 02:32:08,217 EPOCH 7 done: loss 0.0206 - lr: 0.000053
2023-10-12 02:32:28,843 DEV : loss 0.2012760192155838 - f1-score (micro avg) 0.7981
2023-10-12 02:32:28,873 saving best model
2023-10-12 02:32:31,463 ----------------------------------------------------------------------------------------------------
2023-10-12 02:33:25,115 epoch 8 - iter 178/1786 - loss 0.02276046 - time (sec): 53.65 - samples/sec: 466.86 - lr: 0.000052 - momentum: 0.000000
2023-10-12 02:34:19,214 epoch 8 - iter 356/1786 - loss 0.01914228 - time (sec): 107.75 - samples/sec: 466.87 - lr: 0.000050 - momentum: 0.000000
2023-10-12 02:35:14,651 epoch 8 - iter 534/1786 - loss 0.01763461 - time (sec): 163.18 - samples/sec: 460.55 - lr: 0.000048 - momentum: 0.000000
2023-10-12 02:36:05,888 epoch 8 - iter 712/1786 - loss 0.01587325 - time (sec): 214.42 - samples/sec: 458.52 - lr: 0.000046 - momentum: 0.000000
2023-10-12 02:36:56,876 epoch 8 - iter 890/1786 - loss 0.01556667 - time (sec): 265.41 - samples/sec: 459.13 - lr: 0.000044 - momentum: 0.000000
2023-10-12 02:37:50,858 epoch 8 - iter 1068/1786 - loss 0.01500536 - time (sec): 319.39 - samples/sec: 463.67 - lr: 0.000043 - momentum: 0.000000
2023-10-12 02:38:42,418 epoch 8 - iter 1246/1786 - loss 0.01483176 - time (sec): 370.95 - samples/sec: 461.23 - lr: 0.000041 - momentum: 0.000000
2023-10-12 02:39:40,033 epoch 8 - iter 1424/1786 - loss 0.01450104 - time (sec): 428.57 - samples/sec: 460.07 - lr: 0.000039 - momentum: 0.000000
2023-10-12 02:40:35,374 epoch 8 - iter 1602/1786 - loss 0.01489033 - time (sec): 483.91 - samples/sec: 461.79 - lr: 0.000037 - momentum: 0.000000
2023-10-12 02:41:31,522 epoch 8 - iter 1780/1786 - loss 0.01450964 - time (sec): 540.05 - samples/sec: 459.03 - lr: 0.000036 - momentum: 0.000000
2023-10-12 02:41:33,346 ----------------------------------------------------------------------------------------------------
2023-10-12 02:41:33,347 EPOCH 8 done: loss 0.0145 - lr: 0.000036
2023-10-12 02:41:58,535 DEV : loss 0.2015368640422821 - f1-score (micro avg) 0.8133
2023-10-12 02:41:58,571 saving best model
2023-10-12 02:42:01,252 ----------------------------------------------------------------------------------------------------
2023-10-12 02:42:54,587 epoch 9 - iter 178/1786 - loss 0.00872584 - time (sec): 53.33 - samples/sec: 486.07 - lr: 0.000034 - momentum: 0.000000
2023-10-12 02:43:46,379 epoch 9 - iter 356/1786 - loss 0.00630023 - time (sec): 105.12 - samples/sec: 475.08 - lr: 0.000032 - momentum: 0.000000
2023-10-12 02:44:39,948 epoch 9 - iter 534/1786 - loss 0.00756441 - time (sec): 158.69 - samples/sec: 468.31 - lr: 0.000030 - momentum: 0.000000
2023-10-12 02:45:33,997 epoch 9 - iter 712/1786 - loss 0.00695522 - time (sec): 212.74 - samples/sec: 462.16 - lr: 0.000028 - momentum: 0.000000
2023-10-12 02:46:30,457 epoch 9 - iter 890/1786 - loss 0.00724403 - time (sec): 269.20 - samples/sec: 456.26 - lr: 0.000027 - momentum: 0.000000
2023-10-12 02:47:24,449 epoch 9 - iter 1068/1786 - loss 0.00812575 - time (sec): 323.19 - samples/sec: 461.32 - lr: 0.000025 - momentum: 0.000000
2023-10-12 02:48:19,624 epoch 9 - iter 1246/1786 - loss 0.00937037 - time (sec): 378.37 - samples/sec: 463.37 - lr: 0.000023 - momentum: 0.000000
2023-10-12 02:49:13,453 epoch 9 - iter 1424/1786 - loss 0.00930061 - time (sec): 432.20 - samples/sec: 463.61 - lr: 0.000021 - momentum: 0.000000
2023-10-12 02:50:05,206 epoch 9 - iter 1602/1786 - loss 0.00976462 - time (sec): 483.95 - samples/sec: 463.83 - lr: 0.000020 - momentum: 0.000000
2023-10-12 02:51:00,266 epoch 9 - iter 1780/1786 - loss 0.00953790 - time (sec): 539.01 - samples/sec: 460.23 - lr: 0.000018 - momentum: 0.000000
2023-10-12 02:51:02,088 ----------------------------------------------------------------------------------------------------
2023-10-12 02:51:02,088 EPOCH 9 done: loss 0.0095 - lr: 0.000018
2023-10-12 02:51:23,679 DEV : loss 0.2193737030029297 - f1-score (micro avg) 0.8133
2023-10-12 02:51:23,714 ----------------------------------------------------------------------------------------------------
2023-10-12 02:52:17,448 epoch 10 - iter 178/1786 - loss 0.00370170 - time (sec): 53.73 - samples/sec: 469.72 - lr: 0.000016 - momentum: 0.000000
2023-10-12 02:53:11,609 epoch 10 - iter 356/1786 - loss 0.00580275 - time (sec): 107.89 - samples/sec: 468.02 - lr: 0.000014 - momentum: 0.000000
2023-10-12 02:54:05,708 epoch 10 - iter 534/1786 - loss 0.00544806 - time (sec): 161.99 - samples/sec: 468.33 - lr: 0.000012 - momentum: 0.000000
2023-10-12 02:54:59,294 epoch 10 - iter 712/1786 - loss 0.00565942 - time (sec): 215.58 - samples/sec: 469.11 - lr: 0.000011 - momentum: 0.000000
2023-10-12 02:55:53,156 epoch 10 - iter 890/1786 - loss 0.00585775 - time (sec): 269.44 - samples/sec: 469.40 - lr: 0.000009 - momentum: 0.000000
2023-10-12 02:56:46,577 epoch 10 - iter 1068/1786 - loss 0.00554799 - time (sec): 322.86 - samples/sec: 466.02 - lr: 0.000007 - momentum: 0.000000
2023-10-12 02:57:40,202 epoch 10 - iter 1246/1786 - loss 0.00618939 - time (sec): 376.49 - samples/sec: 468.04 - lr: 0.000005 - momentum: 0.000000
2023-10-12 02:58:32,386 epoch 10 - iter 1424/1786 - loss 0.00593712 - time (sec): 428.67 - samples/sec: 467.12 - lr: 0.000004 - momentum: 0.000000
2023-10-12 02:59:24,805 epoch 10 - iter 1602/1786 - loss 0.00597006 - time (sec): 481.09 - samples/sec: 466.32 - lr: 0.000002 - momentum: 0.000000
2023-10-12 03:00:19,462 epoch 10 - iter 1780/1786 - loss 0.00611996 - time (sec): 535.75 - samples/sec: 463.25 - lr: 0.000000 - momentum: 0.000000
2023-10-12 03:00:20,969 ----------------------------------------------------------------------------------------------------
2023-10-12 03:00:20,970 EPOCH 10 done: loss 0.0061 - lr: 0.000000
2023-10-12 03:00:43,438 DEV : loss 0.2238311767578125 - f1-score (micro avg) 0.8046
2023-10-12 03:00:44,547 ----------------------------------------------------------------------------------------------------
2023-10-12 03:00:44,549 Loading model from best epoch ...
2023-10-12 03:00:48,482 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
2023-10-12 03:02:01,023
Results:
- F-score (micro) 0.7119
- F-score (macro) 0.6266
- Accuracy 0.5663
By class:
precision recall f1-score support
LOC 0.7359 0.7251 0.7305 1095
PER 0.7911 0.7747 0.7828 1012
ORG 0.4551 0.5826 0.5111 357
HumanProd 0.4000 0.6061 0.4819 33
micro avg 0.7008 0.7233 0.7119 2497
macro avg 0.5955 0.6721 0.6266 2497
weighted avg 0.7137 0.7233 0.7170 2497
2023-10-12 03:02:01,023 ----------------------------------------------------------------------------------------------------
|