thenlpresearcher/bert-punctuation-restoration-kaustubh
Browse files- README.md +142 -0
- config.json +99 -0
- model.safetensors +3 -0
- runs/Nov03_13-29-48_da1f5c763b14/events.out.tfevents.1762176590.da1f5c763b14.2503.0 +3 -0
- runs/Nov03_13-40-02_da1f5c763b14/events.out.tfevents.1762177203.da1f5c763b14.2503.1 +3 -0
- runs/Nov03_13-41-51_da1f5c763b14/events.out.tfevents.1762177311.da1f5c763b14.2503.2 +3 -0
- runs/Nov03_13-44-50_da1f5c763b14/events.out.tfevents.1762177490.da1f5c763b14.2503.3 +3 -0
- runs/Nov03_13-45-28_da1f5c763b14/events.out.tfevents.1762177529.da1f5c763b14.2503.4 +3 -0
- runs/Nov03_13-45-28_da1f5c763b14/events.out.tfevents.1762181280.da1f5c763b14.2503.5 +3 -0
- runs/Nov22_08-33-36_ca85e5befb5e/events.out.tfevents.1763800416.ca85e5befb5e.50032.0 +3 -0
- runs/Nov22_08-34-31_ca85e5befb5e/events.out.tfevents.1763800472.ca85e5befb5e.50032.1 +3 -0
- runs/Nov22_08-34-41_ca85e5befb5e/events.out.tfevents.1763800482.ca85e5befb5e.50032.2 +3 -0
- runs/Nov22_08-36-19_ca85e5befb5e/events.out.tfevents.1763800580.ca85e5befb5e.50389.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: bert-large-uncased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
model-index:
|
| 12 |
+
- name: bert_punct_model
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# bert_punct_model
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1454
|
| 24 |
+
- F1: 0.8223
|
| 25 |
+
- Precision: 0.8256
|
| 26 |
+
- Recall: 0.8190
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 5e-05
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 16
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 3
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|
| 57 |
+
|:-------------:|:------:|:-----:|:---------------:|:------:|:---------:|:------:|
|
| 58 |
+
| 0.2214 | 0.0388 | 500 | 0.1982 | 0.7598 | 0.7509 | 0.7690 |
|
| 59 |
+
| 0.1839 | 0.0776 | 1000 | 0.1660 | 0.7803 | 0.7938 | 0.7672 |
|
| 60 |
+
| 0.1741 | 0.1164 | 1500 | 0.1612 | 0.7849 | 0.8155 | 0.7566 |
|
| 61 |
+
| 0.1546 | 0.1553 | 2000 | 0.1631 | 0.7884 | 0.7757 | 0.8015 |
|
| 62 |
+
| 0.1575 | 0.1941 | 2500 | 0.1598 | 0.7864 | 0.7841 | 0.7887 |
|
| 63 |
+
| 0.1729 | 0.2329 | 3000 | 0.1551 | 0.7886 | 0.8045 | 0.7734 |
|
| 64 |
+
| 0.1463 | 0.2717 | 3500 | 0.1480 | 0.7912 | 0.7970 | 0.7854 |
|
| 65 |
+
| 0.1379 | 0.3105 | 4000 | 0.1446 | 0.7938 | 0.7994 | 0.7883 |
|
| 66 |
+
| 0.1491 | 0.3493 | 4500 | 0.1470 | 0.7971 | 0.8206 | 0.7748 |
|
| 67 |
+
| 0.1384 | 0.3881 | 5000 | 0.1411 | 0.7972 | 0.8148 | 0.7803 |
|
| 68 |
+
| 0.1455 | 0.4270 | 5500 | 0.1394 | 0.8036 | 0.8210 | 0.7869 |
|
| 69 |
+
| 0.1397 | 0.4658 | 6000 | 0.1419 | 0.8068 | 0.8274 | 0.7872 |
|
| 70 |
+
| 0.1433 | 0.5046 | 6500 | 0.1407 | 0.7974 | 0.8271 | 0.7697 |
|
| 71 |
+
| 0.135 | 0.5434 | 7000 | 0.1359 | 0.8065 | 0.8292 | 0.7850 |
|
| 72 |
+
| 0.1411 | 0.5822 | 7500 | 0.1446 | 0.8030 | 0.8164 | 0.7901 |
|
| 73 |
+
| 0.1415 | 0.6210 | 8000 | 0.1450 | 0.7994 | 0.8003 | 0.7985 |
|
| 74 |
+
| 0.1379 | 0.6598 | 8500 | 0.1441 | 0.8017 | 0.7915 | 0.8120 |
|
| 75 |
+
| 0.1399 | 0.6986 | 9000 | 0.1328 | 0.8116 | 0.8354 | 0.7891 |
|
| 76 |
+
| 0.132 | 0.7375 | 9500 | 0.1357 | 0.8029 | 0.8168 | 0.7894 |
|
| 77 |
+
| 0.1355 | 0.7763 | 10000 | 0.1367 | 0.8100 | 0.8248 | 0.7956 |
|
| 78 |
+
| 0.1342 | 0.8151 | 10500 | 0.1367 | 0.8087 | 0.8153 | 0.8022 |
|
| 79 |
+
| 0.1292 | 0.8539 | 11000 | 0.1344 | 0.8088 | 0.8164 | 0.8015 |
|
| 80 |
+
| 0.1301 | 0.8927 | 11500 | 0.1323 | 0.8194 | 0.8303 | 0.8088 |
|
| 81 |
+
| 0.1282 | 0.9315 | 12000 | 0.1319 | 0.8111 | 0.8249 | 0.7978 |
|
| 82 |
+
| 0.1265 | 0.9703 | 12500 | 0.1367 | 0.8120 | 0.8202 | 0.8040 |
|
| 83 |
+
| 0.1156 | 1.0092 | 13000 | 0.1354 | 0.8108 | 0.8137 | 0.8080 |
|
| 84 |
+
| 0.1068 | 1.0480 | 13500 | 0.1375 | 0.8176 | 0.8163 | 0.8190 |
|
| 85 |
+
| 0.1074 | 1.0868 | 14000 | 0.1357 | 0.8146 | 0.8123 | 0.8168 |
|
| 86 |
+
| 0.1011 | 1.1256 | 14500 | 0.1332 | 0.8131 | 0.8141 | 0.8120 |
|
| 87 |
+
| 0.1054 | 1.1644 | 15000 | 0.1364 | 0.8152 | 0.8096 | 0.8208 |
|
| 88 |
+
| 0.1069 | 1.2032 | 15500 | 0.1368 | 0.8174 | 0.8195 | 0.8153 |
|
| 89 |
+
| 0.1069 | 1.2420 | 16000 | 0.1359 | 0.8183 | 0.8231 | 0.8135 |
|
| 90 |
+
| 0.1047 | 1.2809 | 16500 | 0.1286 | 0.8210 | 0.8268 | 0.8153 |
|
| 91 |
+
| 0.1032 | 1.3197 | 17000 | 0.1315 | 0.8116 | 0.8082 | 0.8150 |
|
| 92 |
+
| 0.1021 | 1.3585 | 17500 | 0.1327 | 0.8108 | 0.8082 | 0.8135 |
|
| 93 |
+
| 0.1003 | 1.3973 | 18000 | 0.1315 | 0.8162 | 0.8171 | 0.8153 |
|
| 94 |
+
| 0.0965 | 1.4361 | 18500 | 0.1339 | 0.8136 | 0.8214 | 0.8058 |
|
| 95 |
+
| 0.0966 | 1.4749 | 19000 | 0.1308 | 0.8162 | 0.8204 | 0.8120 |
|
| 96 |
+
| 0.1034 | 1.5137 | 19500 | 0.1354 | 0.8127 | 0.8227 | 0.8029 |
|
| 97 |
+
| 0.1007 | 1.5526 | 20000 | 0.1317 | 0.8150 | 0.8155 | 0.8146 |
|
| 98 |
+
| 0.1056 | 1.5914 | 20500 | 0.1299 | 0.8142 | 0.8232 | 0.8055 |
|
| 99 |
+
| 0.0987 | 1.6302 | 21000 | 0.1332 | 0.8215 | 0.8320 | 0.8113 |
|
| 100 |
+
| 0.1019 | 1.6690 | 21500 | 0.1314 | 0.8214 | 0.8341 | 0.8091 |
|
| 101 |
+
| 0.1046 | 1.7078 | 22000 | 0.1289 | 0.8184 | 0.8287 | 0.8084 |
|
| 102 |
+
| 0.0966 | 1.7466 | 22500 | 0.1321 | 0.8216 | 0.8333 | 0.8102 |
|
| 103 |
+
| 0.1003 | 1.7854 | 23000 | 0.1279 | 0.8191 | 0.8260 | 0.8124 |
|
| 104 |
+
| 0.105 | 1.8243 | 23500 | 0.1302 | 0.8158 | 0.8260 | 0.8058 |
|
| 105 |
+
| 0.0976 | 1.8631 | 24000 | 0.1303 | 0.8178 | 0.8214 | 0.8142 |
|
| 106 |
+
| 0.0965 | 1.9019 | 24500 | 0.1267 | 0.8185 | 0.8258 | 0.8113 |
|
| 107 |
+
| 0.0966 | 1.9407 | 25000 | 0.1275 | 0.8222 | 0.8240 | 0.8204 |
|
| 108 |
+
| 0.099 | 1.9795 | 25500 | 0.1273 | 0.8222 | 0.8319 | 0.8128 |
|
| 109 |
+
| 0.0733 | 2.0183 | 26000 | 0.1439 | 0.8210 | 0.8250 | 0.8172 |
|
| 110 |
+
| 0.0765 | 2.0571 | 26500 | 0.1418 | 0.8172 | 0.8177 | 0.8168 |
|
| 111 |
+
| 0.0708 | 2.0959 | 27000 | 0.1443 | 0.8174 | 0.8211 | 0.8139 |
|
| 112 |
+
| 0.073 | 2.1348 | 27500 | 0.1429 | 0.8209 | 0.8265 | 0.8153 |
|
| 113 |
+
| 0.0787 | 2.1736 | 28000 | 0.1380 | 0.8178 | 0.8191 | 0.8164 |
|
| 114 |
+
| 0.0672 | 2.2124 | 28500 | 0.1423 | 0.8177 | 0.8242 | 0.8113 |
|
| 115 |
+
| 0.0694 | 2.2512 | 29000 | 0.1422 | 0.8185 | 0.8222 | 0.8150 |
|
| 116 |
+
| 0.0715 | 2.2900 | 29500 | 0.1473 | 0.8190 | 0.8172 | 0.8208 |
|
| 117 |
+
| 0.0724 | 2.3288 | 30000 | 0.1412 | 0.8182 | 0.8152 | 0.8212 |
|
| 118 |
+
| 0.0718 | 2.3676 | 30500 | 0.1429 | 0.8192 | 0.8213 | 0.8172 |
|
| 119 |
+
| 0.071 | 2.4065 | 31000 | 0.1427 | 0.8254 | 0.8294 | 0.8215 |
|
| 120 |
+
| 0.0734 | 2.4453 | 31500 | 0.1495 | 0.8225 | 0.8241 | 0.8208 |
|
| 121 |
+
| 0.0733 | 2.4841 | 32000 | 0.1423 | 0.8200 | 0.8262 | 0.8139 |
|
| 122 |
+
| 0.0658 | 2.5229 | 32500 | 0.1447 | 0.8212 | 0.8287 | 0.8139 |
|
| 123 |
+
| 0.0704 | 2.5617 | 33000 | 0.1443 | 0.8215 | 0.8293 | 0.8139 |
|
| 124 |
+
| 0.0683 | 2.6005 | 33500 | 0.1447 | 0.8226 | 0.8252 | 0.8201 |
|
| 125 |
+
| 0.0678 | 2.6393 | 34000 | 0.1464 | 0.8236 | 0.8268 | 0.8204 |
|
| 126 |
+
| 0.0673 | 2.6782 | 34500 | 0.1450 | 0.8239 | 0.8292 | 0.8186 |
|
| 127 |
+
| 0.0679 | 2.7170 | 35000 | 0.1471 | 0.8190 | 0.8215 | 0.8164 |
|
| 128 |
+
| 0.068 | 2.7558 | 35500 | 0.1475 | 0.8207 | 0.8299 | 0.8117 |
|
| 129 |
+
| 0.0676 | 2.7946 | 36000 | 0.1466 | 0.8196 | 0.8225 | 0.8168 |
|
| 130 |
+
| 0.0686 | 2.8334 | 36500 | 0.1441 | 0.8225 | 0.8272 | 0.8179 |
|
| 131 |
+
| 0.0677 | 2.8722 | 37000 | 0.1464 | 0.8222 | 0.8235 | 0.8208 |
|
| 132 |
+
| 0.0714 | 2.9110 | 37500 | 0.1456 | 0.8200 | 0.8218 | 0.8182 |
|
| 133 |
+
| 0.0679 | 2.9499 | 38000 | 0.1465 | 0.8218 | 0.8249 | 0.8186 |
|
| 134 |
+
| 0.0666 | 2.9887 | 38500 | 0.1454 | 0.8223 | 0.8256 | 0.8190 |
|
| 135 |
+
|
| 136 |
+
|
| 137 |
+
### Framework versions
|
| 138 |
+
|
| 139 |
+
- Transformers 4.53.2
|
| 140 |
+
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
|
| 141 |
+
- Datasets 3.6.0
|
| 142 |
+
- Tokenizers 0.21.4
|
config.json
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20",
|
| 33 |
+
"21": "LABEL_21",
|
| 34 |
+
"22": "LABEL_22",
|
| 35 |
+
"23": "LABEL_23",
|
| 36 |
+
"24": "LABEL_24",
|
| 37 |
+
"25": "LABEL_25",
|
| 38 |
+
"26": "LABEL_26",
|
| 39 |
+
"27": "LABEL_27",
|
| 40 |
+
"28": "LABEL_28",
|
| 41 |
+
"29": "LABEL_29",
|
| 42 |
+
"30": "LABEL_30",
|
| 43 |
+
"31": "LABEL_31",
|
| 44 |
+
"32": "LABEL_32",
|
| 45 |
+
"33": "LABEL_33",
|
| 46 |
+
"34": "LABEL_34"
|
| 47 |
+
},
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 4096,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"LABEL_0": 0,
|
| 52 |
+
"LABEL_1": 1,
|
| 53 |
+
"LABEL_10": 10,
|
| 54 |
+
"LABEL_11": 11,
|
| 55 |
+
"LABEL_12": 12,
|
| 56 |
+
"LABEL_13": 13,
|
| 57 |
+
"LABEL_14": 14,
|
| 58 |
+
"LABEL_15": 15,
|
| 59 |
+
"LABEL_16": 16,
|
| 60 |
+
"LABEL_17": 17,
|
| 61 |
+
"LABEL_18": 18,
|
| 62 |
+
"LABEL_19": 19,
|
| 63 |
+
"LABEL_2": 2,
|
| 64 |
+
"LABEL_20": 20,
|
| 65 |
+
"LABEL_21": 21,
|
| 66 |
+
"LABEL_22": 22,
|
| 67 |
+
"LABEL_23": 23,
|
| 68 |
+
"LABEL_24": 24,
|
| 69 |
+
"LABEL_25": 25,
|
| 70 |
+
"LABEL_26": 26,
|
| 71 |
+
"LABEL_27": 27,
|
| 72 |
+
"LABEL_28": 28,
|
| 73 |
+
"LABEL_29": 29,
|
| 74 |
+
"LABEL_3": 3,
|
| 75 |
+
"LABEL_30": 30,
|
| 76 |
+
"LABEL_31": 31,
|
| 77 |
+
"LABEL_32": 32,
|
| 78 |
+
"LABEL_33": 33,
|
| 79 |
+
"LABEL_34": 34,
|
| 80 |
+
"LABEL_4": 4,
|
| 81 |
+
"LABEL_5": 5,
|
| 82 |
+
"LABEL_6": 6,
|
| 83 |
+
"LABEL_7": 7,
|
| 84 |
+
"LABEL_8": 8,
|
| 85 |
+
"LABEL_9": 9
|
| 86 |
+
},
|
| 87 |
+
"layer_norm_eps": 1e-12,
|
| 88 |
+
"max_position_embeddings": 512,
|
| 89 |
+
"model_type": "bert",
|
| 90 |
+
"num_attention_heads": 16,
|
| 91 |
+
"num_hidden_layers": 24,
|
| 92 |
+
"pad_token_id": 0,
|
| 93 |
+
"position_embedding_type": "absolute",
|
| 94 |
+
"torch_dtype": "float32",
|
| 95 |
+
"transformers_version": "4.53.2",
|
| 96 |
+
"type_vocab_size": 2,
|
| 97 |
+
"use_cache": true,
|
| 98 |
+
"vocab_size": 30522
|
| 99 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69420afd29773f98970213232adec8d204b56a2782a8105663eee077bdc46ce0
|
| 3 |
+
size 1336559468
|
runs/Nov03_13-29-48_da1f5c763b14/events.out.tfevents.1762176590.da1f5c763b14.2503.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1b7745722c81da2a5dfa6f1f8a76a53eadf8d40cf1bd0571e1acdd7ec3d3fbf
|
| 3 |
+
size 6376
|
runs/Nov03_13-40-02_da1f5c763b14/events.out.tfevents.1762177203.da1f5c763b14.2503.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b647d79dd2fa26856d72db327e4dc12bd3526485e2164d3dba0faa37143c43f0
|
| 3 |
+
size 6376
|
runs/Nov03_13-41-51_da1f5c763b14/events.out.tfevents.1762177311.da1f5c763b14.2503.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:244dfa48870acf9929dd487ff1c8d538fabb1c54000f417429d0e8758b5b7368
|
| 3 |
+
size 6376
|
runs/Nov03_13-44-50_da1f5c763b14/events.out.tfevents.1762177490.da1f5c763b14.2503.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb985cb05d2fa36610a53379035ff56a22f2f1ac91dc12f9d5272fb15b953e66
|
| 3 |
+
size 6376
|
runs/Nov03_13-45-28_da1f5c763b14/events.out.tfevents.1762177529.da1f5c763b14.2503.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cebad3def353ca45c844e919f11cfa6135356571d6a5e2a70cd744b8d9b7ec40
|
| 3 |
+
size 24838
|
runs/Nov03_13-45-28_da1f5c763b14/events.out.tfevents.1762181280.da1f5c763b14.2503.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85664abd88f423ece548996ae231335fa64dcd1db080b0bfc9b7c5b35da25db6
|
| 3 |
+
size 1720
|
runs/Nov22_08-33-36_ca85e5befb5e/events.out.tfevents.1763800416.ca85e5befb5e.50032.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bbcceb892219d1cc5b24c26a1ec2e71a8a193b848ac1a08ebfe76032d287c88
|
| 3 |
+
size 6425
|
runs/Nov22_08-34-31_ca85e5befb5e/events.out.tfevents.1763800472.ca85e5befb5e.50032.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba19e5152b0009ef22f0ff6840c768eb5bac6d6ddc3cf8c479c61e30afe62c2b
|
| 3 |
+
size 6425
|
runs/Nov22_08-34-41_ca85e5befb5e/events.out.tfevents.1763800482.ca85e5befb5e.50032.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1594dcb83710a4ae99b55c79a5f30d6e09a1ed967210303274817ad2a7d5a260
|
| 3 |
+
size 6425
|
runs/Nov22_08-36-19_ca85e5befb5e/events.out.tfevents.1763800580.ca85e5befb5e.50389.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6b473275ad683b655f6d256c544e308c490ba66d732470f21d402edc0df0fa
|
| 3 |
+
size 80656
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:412aa651c89c0fabc247a3ae4bf65afbd8823d2e71750517cdb4b32b0c847fa1
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|