File size: 25,329 Bytes
c2b34d1 |
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 |
2023-10-11 09:51:51,454 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,456 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 09:51:51,456 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,457 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
2023-10-11 09:51:51,457 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,457 Train: 7142 sentences
2023-10-11 09:51:51,457 (train_with_dev=False, train_with_test=False)
2023-10-11 09:51:51,457 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,457 Training Params:
2023-10-11 09:51:51,457 - learning_rate: "0.00016"
2023-10-11 09:51:51,457 - mini_batch_size: "8"
2023-10-11 09:51:51,457 - max_epochs: "10"
2023-10-11 09:51:51,457 - shuffle: "True"
2023-10-11 09:51:51,457 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,457 Plugins:
2023-10-11 09:51:51,458 - TensorboardLogger
2023-10-11 09:51:51,458 - LinearScheduler | warmup_fraction: '0.1'
2023-10-11 09:51:51,458 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,458 Final evaluation on model from best epoch (best-model.pt)
2023-10-11 09:51:51,458 - metric: "('micro avg', 'f1-score')"
2023-10-11 09:51:51,458 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,458 Computation:
2023-10-11 09:51:51,458 - compute on device: cuda:0
2023-10-11 09:51:51,458 - embedding storage: none
2023-10-11 09:51:51,458 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,458 Model training base path: "hmbench-newseye/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-3"
2023-10-11 09:51:51,458 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,458 ----------------------------------------------------------------------------------------------------
2023-10-11 09:51:51,459 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-11 09:52:43,650 epoch 1 - iter 89/893 - loss 2.81958198 - time (sec): 52.19 - samples/sec: 515.94 - lr: 0.000016 - momentum: 0.000000
2023-10-11 09:53:33,684 epoch 1 - iter 178/893 - loss 2.73966772 - time (sec): 102.22 - samples/sec: 495.89 - lr: 0.000032 - momentum: 0.000000
2023-10-11 09:54:24,264 epoch 1 - iter 267/893 - loss 2.54471735 - time (sec): 152.80 - samples/sec: 487.65 - lr: 0.000048 - momentum: 0.000000
2023-10-11 09:55:14,301 epoch 1 - iter 356/893 - loss 2.32649706 - time (sec): 202.84 - samples/sec: 486.76 - lr: 0.000064 - momentum: 0.000000
2023-10-11 09:56:05,159 epoch 1 - iter 445/893 - loss 2.08476844 - time (sec): 253.70 - samples/sec: 492.21 - lr: 0.000080 - momentum: 0.000000
2023-10-11 09:56:55,867 epoch 1 - iter 534/893 - loss 1.86965509 - time (sec): 304.41 - samples/sec: 488.69 - lr: 0.000095 - momentum: 0.000000
2023-10-11 09:57:49,598 epoch 1 - iter 623/893 - loss 1.68007860 - time (sec): 358.14 - samples/sec: 486.88 - lr: 0.000111 - momentum: 0.000000
2023-10-11 09:58:44,484 epoch 1 - iter 712/893 - loss 1.52983259 - time (sec): 413.02 - samples/sec: 481.46 - lr: 0.000127 - momentum: 0.000000
2023-10-11 09:59:39,435 epoch 1 - iter 801/893 - loss 1.39878794 - time (sec): 467.97 - samples/sec: 478.76 - lr: 0.000143 - momentum: 0.000000
2023-10-11 10:00:28,196 epoch 1 - iter 890/893 - loss 1.29860971 - time (sec): 516.74 - samples/sec: 479.81 - lr: 0.000159 - momentum: 0.000000
2023-10-11 10:00:29,735 ----------------------------------------------------------------------------------------------------
2023-10-11 10:00:29,736 EPOCH 1 done: loss 1.2953 - lr: 0.000159
2023-10-11 10:00:49,291 DEV : loss 0.23720598220825195 - f1-score (micro avg) 0.521
2023-10-11 10:00:49,321 saving best model
2023-10-11 10:00:50,224 ----------------------------------------------------------------------------------------------------
2023-10-11 10:01:41,521 epoch 2 - iter 89/893 - loss 0.24156291 - time (sec): 51.29 - samples/sec: 511.50 - lr: 0.000158 - momentum: 0.000000
2023-10-11 10:02:32,514 epoch 2 - iter 178/893 - loss 0.23973758 - time (sec): 102.29 - samples/sec: 503.29 - lr: 0.000156 - momentum: 0.000000
2023-10-11 10:03:23,339 epoch 2 - iter 267/893 - loss 0.22533212 - time (sec): 153.11 - samples/sec: 492.16 - lr: 0.000155 - momentum: 0.000000
2023-10-11 10:04:15,696 epoch 2 - iter 356/893 - loss 0.20433271 - time (sec): 205.47 - samples/sec: 490.36 - lr: 0.000153 - momentum: 0.000000
2023-10-11 10:05:06,103 epoch 2 - iter 445/893 - loss 0.19447693 - time (sec): 255.88 - samples/sec: 486.27 - lr: 0.000151 - momentum: 0.000000
2023-10-11 10:06:00,826 epoch 2 - iter 534/893 - loss 0.18500783 - time (sec): 310.60 - samples/sec: 483.67 - lr: 0.000149 - momentum: 0.000000
2023-10-11 10:06:55,207 epoch 2 - iter 623/893 - loss 0.17866349 - time (sec): 364.98 - samples/sec: 478.57 - lr: 0.000148 - momentum: 0.000000
2023-10-11 10:07:46,050 epoch 2 - iter 712/893 - loss 0.17165749 - time (sec): 415.82 - samples/sec: 476.07 - lr: 0.000146 - momentum: 0.000000
2023-10-11 10:08:40,495 epoch 2 - iter 801/893 - loss 0.16565209 - time (sec): 470.27 - samples/sec: 473.21 - lr: 0.000144 - momentum: 0.000000
2023-10-11 10:09:35,309 epoch 2 - iter 890/893 - loss 0.15984826 - time (sec): 525.08 - samples/sec: 472.17 - lr: 0.000142 - momentum: 0.000000
2023-10-11 10:09:36,886 ----------------------------------------------------------------------------------------------------
2023-10-11 10:09:36,887 EPOCH 2 done: loss 0.1596 - lr: 0.000142
2023-10-11 10:09:58,231 DEV : loss 0.09981917589902878 - f1-score (micro avg) 0.7588
2023-10-11 10:09:58,264 saving best model
2023-10-11 10:10:00,886 ----------------------------------------------------------------------------------------------------
2023-10-11 10:10:52,118 epoch 3 - iter 89/893 - loss 0.06769040 - time (sec): 51.23 - samples/sec: 465.50 - lr: 0.000140 - momentum: 0.000000
2023-10-11 10:11:42,503 epoch 3 - iter 178/893 - loss 0.06730058 - time (sec): 101.61 - samples/sec: 481.27 - lr: 0.000139 - momentum: 0.000000
2023-10-11 10:12:32,365 epoch 3 - iter 267/893 - loss 0.06608996 - time (sec): 151.47 - samples/sec: 483.16 - lr: 0.000137 - momentum: 0.000000
2023-10-11 10:13:22,493 epoch 3 - iter 356/893 - loss 0.06822392 - time (sec): 201.60 - samples/sec: 487.02 - lr: 0.000135 - momentum: 0.000000
2023-10-11 10:14:13,138 epoch 3 - iter 445/893 - loss 0.07122185 - time (sec): 252.25 - samples/sec: 487.15 - lr: 0.000133 - momentum: 0.000000
2023-10-11 10:15:03,603 epoch 3 - iter 534/893 - loss 0.07293485 - time (sec): 302.71 - samples/sec: 487.29 - lr: 0.000132 - momentum: 0.000000
2023-10-11 10:15:59,820 epoch 3 - iter 623/893 - loss 0.07412771 - time (sec): 358.93 - samples/sec: 485.22 - lr: 0.000130 - momentum: 0.000000
2023-10-11 10:16:54,820 epoch 3 - iter 712/893 - loss 0.07275147 - time (sec): 413.93 - samples/sec: 478.54 - lr: 0.000128 - momentum: 0.000000
2023-10-11 10:17:50,647 epoch 3 - iter 801/893 - loss 0.07101037 - time (sec): 469.76 - samples/sec: 475.21 - lr: 0.000126 - momentum: 0.000000
2023-10-11 10:18:45,676 epoch 3 - iter 890/893 - loss 0.07076952 - time (sec): 524.78 - samples/sec: 472.85 - lr: 0.000125 - momentum: 0.000000
2023-10-11 10:18:47,139 ----------------------------------------------------------------------------------------------------
2023-10-11 10:18:47,140 EPOCH 3 done: loss 0.0709 - lr: 0.000125
2023-10-11 10:19:08,915 DEV : loss 0.10631939768791199 - f1-score (micro avg) 0.7909
2023-10-11 10:19:08,960 saving best model
2023-10-11 10:19:11,681 ----------------------------------------------------------------------------------------------------
2023-10-11 10:20:04,148 epoch 4 - iter 89/893 - loss 0.04488972 - time (sec): 52.46 - samples/sec: 457.96 - lr: 0.000123 - momentum: 0.000000
2023-10-11 10:20:59,199 epoch 4 - iter 178/893 - loss 0.04859362 - time (sec): 107.51 - samples/sec: 455.92 - lr: 0.000121 - momentum: 0.000000
2023-10-11 10:21:55,697 epoch 4 - iter 267/893 - loss 0.04714332 - time (sec): 164.01 - samples/sec: 461.00 - lr: 0.000119 - momentum: 0.000000
2023-10-11 10:22:50,160 epoch 4 - iter 356/893 - loss 0.04851860 - time (sec): 218.47 - samples/sec: 458.60 - lr: 0.000117 - momentum: 0.000000
2023-10-11 10:23:41,893 epoch 4 - iter 445/893 - loss 0.04963523 - time (sec): 270.21 - samples/sec: 465.48 - lr: 0.000116 - momentum: 0.000000
2023-10-11 10:24:30,632 epoch 4 - iter 534/893 - loss 0.05027391 - time (sec): 318.95 - samples/sec: 466.00 - lr: 0.000114 - momentum: 0.000000
2023-10-11 10:25:19,741 epoch 4 - iter 623/893 - loss 0.05064819 - time (sec): 368.06 - samples/sec: 472.03 - lr: 0.000112 - momentum: 0.000000
2023-10-11 10:26:11,200 epoch 4 - iter 712/893 - loss 0.05119551 - time (sec): 419.51 - samples/sec: 471.86 - lr: 0.000110 - momentum: 0.000000
2023-10-11 10:27:01,611 epoch 4 - iter 801/893 - loss 0.05054556 - time (sec): 469.93 - samples/sec: 474.73 - lr: 0.000109 - momentum: 0.000000
2023-10-11 10:27:52,358 epoch 4 - iter 890/893 - loss 0.04922809 - time (sec): 520.67 - samples/sec: 476.32 - lr: 0.000107 - momentum: 0.000000
2023-10-11 10:27:53,878 ----------------------------------------------------------------------------------------------------
2023-10-11 10:27:53,879 EPOCH 4 done: loss 0.0491 - lr: 0.000107
2023-10-11 10:28:16,061 DEV : loss 0.13096819818019867 - f1-score (micro avg) 0.7973
2023-10-11 10:28:16,097 saving best model
2023-10-11 10:28:18,714 ----------------------------------------------------------------------------------------------------
2023-10-11 10:29:14,514 epoch 5 - iter 89/893 - loss 0.03067518 - time (sec): 55.79 - samples/sec: 450.15 - lr: 0.000105 - momentum: 0.000000
2023-10-11 10:30:10,324 epoch 5 - iter 178/893 - loss 0.03624382 - time (sec): 111.61 - samples/sec: 453.36 - lr: 0.000103 - momentum: 0.000000
2023-10-11 10:31:01,711 epoch 5 - iter 267/893 - loss 0.03352199 - time (sec): 162.99 - samples/sec: 464.01 - lr: 0.000101 - momentum: 0.000000
2023-10-11 10:31:50,487 epoch 5 - iter 356/893 - loss 0.03375946 - time (sec): 211.77 - samples/sec: 470.97 - lr: 0.000100 - momentum: 0.000000
2023-10-11 10:32:40,342 epoch 5 - iter 445/893 - loss 0.03395690 - time (sec): 261.62 - samples/sec: 472.45 - lr: 0.000098 - momentum: 0.000000
2023-10-11 10:33:31,750 epoch 5 - iter 534/893 - loss 0.03542389 - time (sec): 313.03 - samples/sec: 471.58 - lr: 0.000096 - momentum: 0.000000
2023-10-11 10:34:28,397 epoch 5 - iter 623/893 - loss 0.03472368 - time (sec): 369.68 - samples/sec: 467.82 - lr: 0.000094 - momentum: 0.000000
2023-10-11 10:35:18,765 epoch 5 - iter 712/893 - loss 0.03520394 - time (sec): 420.05 - samples/sec: 469.87 - lr: 0.000093 - momentum: 0.000000
2023-10-11 10:36:13,262 epoch 5 - iter 801/893 - loss 0.03464309 - time (sec): 474.54 - samples/sec: 468.46 - lr: 0.000091 - momentum: 0.000000
2023-10-11 10:37:02,901 epoch 5 - iter 890/893 - loss 0.03596866 - time (sec): 524.18 - samples/sec: 473.24 - lr: 0.000089 - momentum: 0.000000
2023-10-11 10:37:04,415 ----------------------------------------------------------------------------------------------------
2023-10-11 10:37:04,415 EPOCH 5 done: loss 0.0360 - lr: 0.000089
2023-10-11 10:37:25,634 DEV : loss 0.14307744801044464 - f1-score (micro avg) 0.8043
2023-10-11 10:37:25,663 saving best model
2023-10-11 10:37:28,263 ----------------------------------------------------------------------------------------------------
2023-10-11 10:38:18,809 epoch 6 - iter 89/893 - loss 0.03174465 - time (sec): 50.54 - samples/sec: 514.67 - lr: 0.000087 - momentum: 0.000000
2023-10-11 10:39:07,991 epoch 6 - iter 178/893 - loss 0.02928006 - time (sec): 99.72 - samples/sec: 497.76 - lr: 0.000085 - momentum: 0.000000
2023-10-11 10:39:57,896 epoch 6 - iter 267/893 - loss 0.02968319 - time (sec): 149.63 - samples/sec: 492.29 - lr: 0.000084 - momentum: 0.000000
2023-10-11 10:40:49,294 epoch 6 - iter 356/893 - loss 0.02835877 - time (sec): 201.03 - samples/sec: 493.58 - lr: 0.000082 - momentum: 0.000000
2023-10-11 10:41:40,128 epoch 6 - iter 445/893 - loss 0.02693656 - time (sec): 251.86 - samples/sec: 491.28 - lr: 0.000080 - momentum: 0.000000
2023-10-11 10:42:30,558 epoch 6 - iter 534/893 - loss 0.02653119 - time (sec): 302.29 - samples/sec: 486.48 - lr: 0.000078 - momentum: 0.000000
2023-10-11 10:43:21,338 epoch 6 - iter 623/893 - loss 0.02667286 - time (sec): 353.07 - samples/sec: 486.64 - lr: 0.000077 - momentum: 0.000000
2023-10-11 10:44:12,346 epoch 6 - iter 712/893 - loss 0.02748104 - time (sec): 404.08 - samples/sec: 490.38 - lr: 0.000075 - momentum: 0.000000
2023-10-11 10:45:00,449 epoch 6 - iter 801/893 - loss 0.02718055 - time (sec): 452.18 - samples/sec: 493.59 - lr: 0.000073 - momentum: 0.000000
2023-10-11 10:45:49,594 epoch 6 - iter 890/893 - loss 0.02706511 - time (sec): 501.33 - samples/sec: 494.82 - lr: 0.000071 - momentum: 0.000000
2023-10-11 10:45:51,093 ----------------------------------------------------------------------------------------------------
2023-10-11 10:45:51,093 EPOCH 6 done: loss 0.0270 - lr: 0.000071
2023-10-11 10:46:11,841 DEV : loss 0.1740272492170334 - f1-score (micro avg) 0.7989
2023-10-11 10:46:11,871 ----------------------------------------------------------------------------------------------------
2023-10-11 10:46:59,408 epoch 7 - iter 89/893 - loss 0.02529529 - time (sec): 47.53 - samples/sec: 515.71 - lr: 0.000069 - momentum: 0.000000
2023-10-11 10:47:48,889 epoch 7 - iter 178/893 - loss 0.02618348 - time (sec): 97.02 - samples/sec: 492.54 - lr: 0.000068 - momentum: 0.000000
2023-10-11 10:48:38,830 epoch 7 - iter 267/893 - loss 0.02283278 - time (sec): 146.96 - samples/sec: 497.17 - lr: 0.000066 - momentum: 0.000000
2023-10-11 10:49:27,859 epoch 7 - iter 356/893 - loss 0.02247875 - time (sec): 195.99 - samples/sec: 495.73 - lr: 0.000064 - momentum: 0.000000
2023-10-11 10:50:20,268 epoch 7 - iter 445/893 - loss 0.02349580 - time (sec): 248.39 - samples/sec: 492.55 - lr: 0.000062 - momentum: 0.000000
2023-10-11 10:51:11,607 epoch 7 - iter 534/893 - loss 0.02280138 - time (sec): 299.73 - samples/sec: 493.64 - lr: 0.000061 - momentum: 0.000000
2023-10-11 10:52:02,733 epoch 7 - iter 623/893 - loss 0.02188778 - time (sec): 350.86 - samples/sec: 493.14 - lr: 0.000059 - momentum: 0.000000
2023-10-11 10:52:55,211 epoch 7 - iter 712/893 - loss 0.02139551 - time (sec): 403.34 - samples/sec: 491.20 - lr: 0.000057 - momentum: 0.000000
2023-10-11 10:53:47,078 epoch 7 - iter 801/893 - loss 0.02130839 - time (sec): 455.20 - samples/sec: 490.46 - lr: 0.000055 - momentum: 0.000000
2023-10-11 10:54:40,102 epoch 7 - iter 890/893 - loss 0.02103175 - time (sec): 508.23 - samples/sec: 488.30 - lr: 0.000053 - momentum: 0.000000
2023-10-11 10:54:41,689 ----------------------------------------------------------------------------------------------------
2023-10-11 10:54:41,689 EPOCH 7 done: loss 0.0211 - lr: 0.000053
2023-10-11 10:55:04,149 DEV : loss 0.17123691737651825 - f1-score (micro avg) 0.7955
2023-10-11 10:55:04,179 ----------------------------------------------------------------------------------------------------
2023-10-11 10:55:54,180 epoch 8 - iter 89/893 - loss 0.01527667 - time (sec): 50.00 - samples/sec: 493.94 - lr: 0.000052 - momentum: 0.000000
2023-10-11 10:56:44,974 epoch 8 - iter 178/893 - loss 0.01586546 - time (sec): 100.79 - samples/sec: 490.48 - lr: 0.000050 - momentum: 0.000000
2023-10-11 10:57:38,893 epoch 8 - iter 267/893 - loss 0.01414335 - time (sec): 154.71 - samples/sec: 470.32 - lr: 0.000048 - momentum: 0.000000
2023-10-11 10:58:32,085 epoch 8 - iter 356/893 - loss 0.01357556 - time (sec): 207.90 - samples/sec: 462.77 - lr: 0.000046 - momentum: 0.000000
2023-10-11 10:59:27,665 epoch 8 - iter 445/893 - loss 0.01506294 - time (sec): 263.48 - samples/sec: 455.96 - lr: 0.000045 - momentum: 0.000000
2023-10-11 11:00:20,764 epoch 8 - iter 534/893 - loss 0.01614469 - time (sec): 316.58 - samples/sec: 462.89 - lr: 0.000043 - momentum: 0.000000
2023-10-11 11:01:12,150 epoch 8 - iter 623/893 - loss 0.01576585 - time (sec): 367.97 - samples/sec: 468.57 - lr: 0.000041 - momentum: 0.000000
2023-10-11 11:02:04,707 epoch 8 - iter 712/893 - loss 0.01631603 - time (sec): 420.53 - samples/sec: 473.12 - lr: 0.000039 - momentum: 0.000000
2023-10-11 11:02:56,711 epoch 8 - iter 801/893 - loss 0.01698976 - time (sec): 472.53 - samples/sec: 474.98 - lr: 0.000037 - momentum: 0.000000
2023-10-11 11:03:46,712 epoch 8 - iter 890/893 - loss 0.01660442 - time (sec): 522.53 - samples/sec: 474.80 - lr: 0.000036 - momentum: 0.000000
2023-10-11 11:03:48,175 ----------------------------------------------------------------------------------------------------
2023-10-11 11:03:48,176 EPOCH 8 done: loss 0.0166 - lr: 0.000036
2023-10-11 11:04:09,326 DEV : loss 0.1897462159395218 - f1-score (micro avg) 0.8003
2023-10-11 11:04:09,356 ----------------------------------------------------------------------------------------------------
2023-10-11 11:04:59,464 epoch 9 - iter 89/893 - loss 0.01141607 - time (sec): 50.11 - samples/sec: 476.01 - lr: 0.000034 - momentum: 0.000000
2023-10-11 11:05:49,221 epoch 9 - iter 178/893 - loss 0.01061287 - time (sec): 99.86 - samples/sec: 467.98 - lr: 0.000032 - momentum: 0.000000
2023-10-11 11:06:37,768 epoch 9 - iter 267/893 - loss 0.01141794 - time (sec): 148.41 - samples/sec: 463.59 - lr: 0.000030 - momentum: 0.000000
2023-10-11 11:07:31,411 epoch 9 - iter 356/893 - loss 0.01110773 - time (sec): 202.05 - samples/sec: 469.68 - lr: 0.000029 - momentum: 0.000000
2023-10-11 11:08:27,558 epoch 9 - iter 445/893 - loss 0.01210552 - time (sec): 258.20 - samples/sec: 465.79 - lr: 0.000027 - momentum: 0.000000
2023-10-11 11:09:21,450 epoch 9 - iter 534/893 - loss 0.01286214 - time (sec): 312.09 - samples/sec: 468.30 - lr: 0.000025 - momentum: 0.000000
2023-10-11 11:10:14,841 epoch 9 - iter 623/893 - loss 0.01302278 - time (sec): 365.48 - samples/sec: 472.28 - lr: 0.000023 - momentum: 0.000000
2023-10-11 11:11:06,931 epoch 9 - iter 712/893 - loss 0.01261530 - time (sec): 417.57 - samples/sec: 475.71 - lr: 0.000022 - momentum: 0.000000
2023-10-11 11:11:59,563 epoch 9 - iter 801/893 - loss 0.01305653 - time (sec): 470.21 - samples/sec: 475.44 - lr: 0.000020 - momentum: 0.000000
2023-10-11 11:12:49,808 epoch 9 - iter 890/893 - loss 0.01318959 - time (sec): 520.45 - samples/sec: 475.89 - lr: 0.000018 - momentum: 0.000000
2023-10-11 11:12:51,530 ----------------------------------------------------------------------------------------------------
2023-10-11 11:12:51,530 EPOCH 9 done: loss 0.0131 - lr: 0.000018
2023-10-11 11:13:13,077 DEV : loss 0.19762861728668213 - f1-score (micro avg) 0.7971
2023-10-11 11:13:13,107 ----------------------------------------------------------------------------------------------------
2023-10-11 11:14:01,040 epoch 10 - iter 89/893 - loss 0.00903721 - time (sec): 47.93 - samples/sec: 520.50 - lr: 0.000016 - momentum: 0.000000
2023-10-11 11:14:48,169 epoch 10 - iter 178/893 - loss 0.01155862 - time (sec): 95.06 - samples/sec: 506.09 - lr: 0.000014 - momentum: 0.000000
2023-10-11 11:15:36,368 epoch 10 - iter 267/893 - loss 0.01117476 - time (sec): 143.26 - samples/sec: 507.88 - lr: 0.000013 - momentum: 0.000000
2023-10-11 11:16:25,236 epoch 10 - iter 356/893 - loss 0.01092791 - time (sec): 192.13 - samples/sec: 511.73 - lr: 0.000011 - momentum: 0.000000
2023-10-11 11:17:15,043 epoch 10 - iter 445/893 - loss 0.01104186 - time (sec): 241.93 - samples/sec: 513.40 - lr: 0.000009 - momentum: 0.000000
2023-10-11 11:18:03,341 epoch 10 - iter 534/893 - loss 0.01048931 - time (sec): 290.23 - samples/sec: 512.33 - lr: 0.000007 - momentum: 0.000000
2023-10-11 11:18:53,582 epoch 10 - iter 623/893 - loss 0.01050700 - time (sec): 340.47 - samples/sec: 507.21 - lr: 0.000006 - momentum: 0.000000
2023-10-11 11:19:43,252 epoch 10 - iter 712/893 - loss 0.01002609 - time (sec): 390.14 - samples/sec: 506.48 - lr: 0.000004 - momentum: 0.000000
2023-10-11 11:20:33,114 epoch 10 - iter 801/893 - loss 0.00990462 - time (sec): 440.01 - samples/sec: 505.61 - lr: 0.000002 - momentum: 0.000000
2023-10-11 11:21:24,177 epoch 10 - iter 890/893 - loss 0.01009786 - time (sec): 491.07 - samples/sec: 505.52 - lr: 0.000000 - momentum: 0.000000
2023-10-11 11:21:25,540 ----------------------------------------------------------------------------------------------------
2023-10-11 11:21:25,540 EPOCH 10 done: loss 0.0101 - lr: 0.000000
2023-10-11 11:21:46,902 DEV : loss 0.2045479267835617 - f1-score (micro avg) 0.7949
2023-10-11 11:21:47,835 ----------------------------------------------------------------------------------------------------
2023-10-11 11:21:47,837 Loading model from best epoch ...
2023-10-11 11:21:51,551 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
2023-10-11 11:23:00,255
Results:
- F-score (micro) 0.6987
- F-score (macro) 0.6131
- Accuracy 0.5529
By class:
precision recall f1-score support
LOC 0.6829 0.7315 0.7063 1095
PER 0.7810 0.7717 0.7763 1012
ORG 0.4562 0.5686 0.5062 357
HumanProd 0.3878 0.5758 0.4634 33
micro avg 0.6764 0.7225 0.6987 2497
macro avg 0.5769 0.6619 0.6131 2497
weighted avg 0.6863 0.7225 0.7029 2497
2023-10-11 11:23:00,255 ----------------------------------------------------------------------------------------------------
|