tona3738/ChungliaoSA_MizoBERT_finetuned
Browse files- README.md +93 -67
- config.json +9 -11
- model.safetensors +2 -2
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# results
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss:
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- F1: 0.
|
| 26 |
-
- Precision: 0.
|
| 27 |
-
- Recall: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -56,65 +56,91 @@ The following hyperparameters were used during training:
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 58 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
|
| 119 |
|
| 120 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: robzchhangte/MizBERT
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 18 |
|
| 19 |
# results
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [robzchhangte/MizBERT](https://huggingface.co/robzchhangte/MizBERT) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.3926
|
| 24 |
+
- Accuracy: 0.725
|
| 25 |
+
- F1: 0.7250
|
| 26 |
+
- Precision: 0.725
|
| 27 |
+
- Recall: 0.725
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 58 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 59 |
+
| 0.7055 | 0.0585 | 10 | 0.7187 | 0.4938 | 0.4938 | 0.4938 | 0.4938 |
|
| 60 |
+
| 0.7246 | 0.1170 | 20 | 0.7049 | 0.4938 | 0.4938 | 0.4938 | 0.4938 |
|
| 61 |
+
| 0.694 | 0.1754 | 30 | 0.6871 | 0.5047 | 0.5047 | 0.5047 | 0.5047 |
|
| 62 |
+
| 0.6795 | 0.2339 | 40 | 0.6711 | 0.5719 | 0.5719 | 0.5719 | 0.5719 |
|
| 63 |
+
| 0.6724 | 0.2924 | 50 | 0.6462 | 0.775 | 0.775 | 0.775 | 0.775 |
|
| 64 |
+
| 0.6381 | 0.3509 | 60 | 0.6175 | 0.6891 | 0.6891 | 0.6891 | 0.6891 |
|
| 65 |
+
| 0.6196 | 0.4094 | 70 | 0.5848 | 0.6703 | 0.6703 | 0.6703 | 0.6703 |
|
| 66 |
+
| 0.5953 | 0.4678 | 80 | 0.5209 | 0.8891 | 0.8891 | 0.8891 | 0.8891 |
|
| 67 |
+
| 0.541 | 0.5263 | 90 | 0.4970 | 0.7766 | 0.7766 | 0.7766 | 0.7766 |
|
| 68 |
+
| 0.4702 | 0.5848 | 100 | 0.4052 | 0.8406 | 0.8406 | 0.8406 | 0.8406 |
|
| 69 |
+
| 0.3675 | 0.6433 | 110 | 0.2772 | 0.925 | 0.925 | 0.925 | 0.925 |
|
| 70 |
+
| 0.2899 | 0.7018 | 120 | 0.2200 | 0.9219 | 0.9219 | 0.9219 | 0.9219 |
|
| 71 |
+
| 0.1951 | 0.7602 | 130 | 0.1902 | 0.9297 | 0.9297 | 0.9297 | 0.9297 |
|
| 72 |
+
| 0.1448 | 0.8187 | 140 | 0.1830 | 0.9359 | 0.9359 | 0.9359 | 0.9359 |
|
| 73 |
+
| 0.3086 | 0.8772 | 150 | 0.1675 | 0.9453 | 0.9453 | 0.9453 | 0.9453 |
|
| 74 |
+
| 0.1802 | 0.9357 | 160 | 0.1632 | 0.9391 | 0.9391 | 0.9391 | 0.9391 |
|
| 75 |
+
| 0.1315 | 0.9942 | 170 | 0.1461 | 0.9516 | 0.9516 | 0.9516 | 0.9516 |
|
| 76 |
+
| 0.0848 | 1.0526 | 180 | 0.1691 | 0.9406 | 0.9406 | 0.9406 | 0.9406 |
|
| 77 |
+
| 0.1519 | 1.1111 | 190 | 0.1660 | 0.9453 | 0.9453 | 0.9453 | 0.9453 |
|
| 78 |
+
| 0.1363 | 1.1696 | 200 | 0.1355 | 0.9563 | 0.9563 | 0.9563 | 0.9563 |
|
| 79 |
+
| 0.1734 | 1.2281 | 210 | 0.1341 | 0.9531 | 0.9531 | 0.9531 | 0.9531 |
|
| 80 |
+
| 0.1234 | 1.2865 | 220 | 0.1225 | 0.9547 | 0.9547 | 0.9547 | 0.9547 |
|
| 81 |
+
| 0.1877 | 1.3450 | 230 | 0.2228 | 0.9219 | 0.9219 | 0.9219 | 0.9219 |
|
| 82 |
+
| 0.125 | 1.4035 | 240 | 0.2108 | 0.9359 | 0.9359 | 0.9359 | 0.9359 |
|
| 83 |
+
| 0.169 | 1.4620 | 250 | 0.1416 | 0.9563 | 0.9563 | 0.9563 | 0.9563 |
|
| 84 |
+
| 0.0852 | 1.5205 | 260 | 0.1722 | 0.9516 | 0.9516 | 0.9516 | 0.9516 |
|
| 85 |
+
| 0.1255 | 1.5789 | 270 | 0.1551 | 0.9609 | 0.9609 | 0.9609 | 0.9609 |
|
| 86 |
+
| 0.1869 | 1.6374 | 280 | 0.1823 | 0.9469 | 0.9469 | 0.9469 | 0.9469 |
|
| 87 |
+
| 0.1286 | 1.6959 | 290 | 0.1334 | 0.9641 | 0.9641 | 0.9641 | 0.9641 |
|
| 88 |
+
| 0.1508 | 1.7544 | 300 | 0.1064 | 0.9703 | 0.9703 | 0.9703 | 0.9703 |
|
| 89 |
+
| 0.1334 | 1.8129 | 310 | 0.0977 | 0.9703 | 0.9703 | 0.9703 | 0.9703 |
|
| 90 |
+
| 0.0937 | 1.8713 | 320 | 0.1685 | 0.9453 | 0.9453 | 0.9453 | 0.9453 |
|
| 91 |
+
| 0.1036 | 1.9298 | 330 | 0.1624 | 0.95 | 0.9500 | 0.95 | 0.95 |
|
| 92 |
+
| 0.084 | 1.9883 | 340 | 0.1674 | 0.9578 | 0.9578 | 0.9578 | 0.9578 |
|
| 93 |
+
| 0.0941 | 2.0468 | 350 | 0.1388 | 0.9672 | 0.9672 | 0.9672 | 0.9672 |
|
| 94 |
+
| 0.0322 | 2.1053 | 360 | 0.1474 | 0.9609 | 0.9609 | 0.9609 | 0.9609 |
|
| 95 |
+
| 0.0538 | 2.1637 | 370 | 0.1744 | 0.9641 | 0.9641 | 0.9641 | 0.9641 |
|
| 96 |
+
| 0.122 | 2.2222 | 380 | 0.1500 | 0.9625 | 0.9625 | 0.9625 | 0.9625 |
|
| 97 |
+
| 0.0953 | 2.2807 | 390 | 0.1452 | 0.9703 | 0.9703 | 0.9703 | 0.9703 |
|
| 98 |
+
| 0.0173 | 2.3392 | 400 | 0.1335 | 0.9703 | 0.9703 | 0.9703 | 0.9703 |
|
| 99 |
+
| 0.1145 | 2.3977 | 410 | 0.1010 | 0.9734 | 0.9734 | 0.9734 | 0.9734 |
|
| 100 |
+
| 0.0869 | 2.4561 | 420 | 0.2181 | 0.9453 | 0.9453 | 0.9453 | 0.9453 |
|
| 101 |
+
| 0.133 | 2.5146 | 430 | 0.1249 | 0.9594 | 0.9594 | 0.9594 | 0.9594 |
|
| 102 |
+
| 0.0906 | 2.5731 | 440 | 0.1398 | 0.9625 | 0.9625 | 0.9625 | 0.9625 |
|
| 103 |
+
| 0.0219 | 2.6316 | 450 | 0.1419 | 0.9656 | 0.9656 | 0.9656 | 0.9656 |
|
| 104 |
+
| 0.019 | 2.6901 | 460 | 0.2162 | 0.9594 | 0.9594 | 0.9594 | 0.9594 |
|
| 105 |
+
| 0.0504 | 2.7485 | 470 | 0.1927 | 0.9625 | 0.9625 | 0.9625 | 0.9625 |
|
| 106 |
+
| 0.0321 | 2.8070 | 480 | 0.1142 | 0.975 | 0.975 | 0.975 | 0.975 |
|
| 107 |
+
| 0.1058 | 2.8655 | 490 | 0.3005 | 0.9359 | 0.9359 | 0.9359 | 0.9359 |
|
| 108 |
+
| 0.0666 | 2.9240 | 500 | 0.2410 | 0.9563 | 0.9563 | 0.9563 | 0.9563 |
|
| 109 |
+
| 0.0383 | 2.9825 | 510 | 0.1155 | 0.9688 | 0.9688 | 0.9688 | 0.9688 |
|
| 110 |
+
| 0.022 | 3.0409 | 520 | 0.0930 | 0.9797 | 0.9797 | 0.9797 | 0.9797 |
|
| 111 |
+
| 0.1328 | 3.0994 | 530 | 0.1120 | 0.975 | 0.975 | 0.975 | 0.975 |
|
| 112 |
+
| 0.0765 | 3.1579 | 540 | 0.0973 | 0.9766 | 0.9766 | 0.9766 | 0.9766 |
|
| 113 |
+
| 0.0316 | 3.2164 | 550 | 0.0939 | 0.9797 | 0.9797 | 0.9797 | 0.9797 |
|
| 114 |
+
| 0.0646 | 3.2749 | 560 | 0.0965 | 0.9812 | 0.9812 | 0.9812 | 0.9812 |
|
| 115 |
+
| 0.0478 | 3.3333 | 570 | 0.0726 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 116 |
+
| 0.0007 | 3.3918 | 580 | 0.0772 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 117 |
+
| 0.0444 | 3.4503 | 590 | 0.0769 | 0.9859 | 0.9859 | 0.9859 | 0.9859 |
|
| 118 |
+
| 0.0378 | 3.5088 | 600 | 0.0773 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 119 |
+
| 0.0058 | 3.5673 | 610 | 0.0932 | 0.9812 | 0.9812 | 0.9812 | 0.9812 |
|
| 120 |
+
| 0.0282 | 3.6257 | 620 | 0.1314 | 0.9703 | 0.9703 | 0.9703 | 0.9703 |
|
| 121 |
+
| 0.0034 | 3.6842 | 630 | 0.1199 | 0.9719 | 0.9719 | 0.9719 | 0.9719 |
|
| 122 |
+
| 0.0485 | 3.7427 | 640 | 0.1164 | 0.9781 | 0.9781 | 0.9781 | 0.9781 |
|
| 123 |
+
| 0.1038 | 3.8012 | 650 | 0.1432 | 0.9781 | 0.9781 | 0.9781 | 0.9781 |
|
| 124 |
+
| 0.0024 | 3.8596 | 660 | 0.1072 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 125 |
+
| 0.0143 | 3.9181 | 670 | 0.1090 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 126 |
+
| 0.0504 | 3.9766 | 680 | 0.1029 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 127 |
+
| 0.0234 | 4.0351 | 690 | 0.0889 | 0.9812 | 0.9812 | 0.9812 | 0.9812 |
|
| 128 |
+
| 0.0005 | 4.0936 | 700 | 0.0847 | 0.9812 | 0.9812 | 0.9812 | 0.9812 |
|
| 129 |
+
| 0.0275 | 4.1520 | 710 | 0.0694 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 130 |
+
| 0.0166 | 4.2105 | 720 | 0.0758 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 131 |
+
| 0.0007 | 4.2690 | 730 | 0.0875 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 132 |
+
| 0.0004 | 4.3275 | 740 | 0.0968 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 133 |
+
| 0.0004 | 4.3860 | 750 | 0.0939 | 0.9812 | 0.9812 | 0.9812 | 0.9812 |
|
| 134 |
+
| 0.0006 | 4.4444 | 760 | 0.0912 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 135 |
+
| 0.0453 | 4.5029 | 770 | 0.0876 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 136 |
+
| 0.0037 | 4.5614 | 780 | 0.0921 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 137 |
+
| 0.0459 | 4.6199 | 790 | 0.1005 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 138 |
+
| 0.0027 | 4.6784 | 800 | 0.1031 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 139 |
+
| 0.0203 | 4.7368 | 810 | 0.0974 | 0.9828 | 0.9828 | 0.9828 | 0.9828 |
|
| 140 |
+
| 0.02 | 4.7953 | 820 | 0.0847 | 0.9859 | 0.9859 | 0.9859 | 0.9859 |
|
| 141 |
+
| 0.0355 | 4.8538 | 830 | 0.0871 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 142 |
+
| 0.0021 | 4.9123 | 840 | 0.0881 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 143 |
+
| 0.0011 | 4.9708 | 850 | 0.0882 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
|
| 144 |
|
| 145 |
|
| 146 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,29 +1,27 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
-
"
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
| 15 |
-
"layer_norm_eps": 1e-
|
| 16 |
-
"max_position_embeddings":
|
| 17 |
-
"model_type": "
|
| 18 |
"num_attention_heads": 12,
|
| 19 |
"num_hidden_layers": 12,
|
| 20 |
-
"
|
| 21 |
-
"pad_token_id": 1,
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"problem_type": "single_label_classification",
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
"transformers_version": "4.42.4",
|
| 26 |
-
"type_vocab_size":
|
| 27 |
"use_cache": true,
|
| 28 |
-
"vocab_size":
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "robzchhangte/MizBERT",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
"num_attention_heads": 12,
|
| 18 |
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
|
|
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"problem_type": "single_label_classification",
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
"transformers_version": "4.42.4",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:189ff4711a18c5c434eedfec5107a408e57e4923e7324580bf6a033577df4b32
|
| 3 |
+
size 437958648
|