trickstar0
commited on
Commit
•
5b58460
1
Parent(s):
79758a9
End of training
Browse files
README.md
CHANGED
@@ -14,15 +14,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [NlpHUST/ner-vietnamese-electra-base](https://huggingface.co/NlpHUST/ner-vietnamese-electra-base) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
-
- Location: {'precision': 0.
|
19 |
-
- Miscellaneous: {'precision': 0.
|
20 |
-
- Organization: {'precision': 0.
|
21 |
-
- Person: {'precision': 0.
|
22 |
-
- Overall Precision: 0.
|
23 |
-
- Overall Recall: 0.
|
24 |
-
- Overall F1: 0.
|
25 |
-
- Overall Accuracy: 0.
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch | Step | Validation Loss | Location
|
55 |
-
|
56 |
-
| No log | 1.0 |
|
57 |
-
| No log | 2.0 |
|
58 |
-
| 0.
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
- Transformers 4.42.4
|
64 |
-
- Pytorch 2.
|
65 |
- Datasets 2.21.0
|
66 |
- Tokenizers 0.19.1
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [NlpHUST/ner-vietnamese-electra-base](https://huggingface.co/NlpHUST/ner-vietnamese-electra-base) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.1569
|
18 |
+
- Location: {'precision': 0.8888888888888888, 'recall': 0.6153846153846154, 'f1': 0.7272727272727274, 'number': 13}
|
19 |
+
- Miscellaneous: {'precision': 0.6255506607929515, 'recall': 0.7029702970297029, 'f1': 0.662004662004662, 'number': 202}
|
20 |
+
- Organization: {'precision': 0.723404255319149, 'recall': 0.7906976744186046, 'f1': 0.7555555555555555, 'number': 43}
|
21 |
+
- Person: {'precision': 0.3157894736842105, 'recall': 0.3157894736842105, 'f1': 0.3157894736842105, 'number': 19}
|
22 |
+
- Overall Precision: 0.6291
|
23 |
+
- Overall Recall: 0.6859
|
24 |
+
- Overall F1: 0.6563
|
25 |
+
- Overall Accuracy: 0.9587
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Location | Miscellaneous | Organization | Person | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
56 |
+
| No log | 1.0 | 220 | 0.1317 | {'precision': 0.6666666666666666, 'recall': 0.46153846153846156, 'f1': 0.5454545454545455, 'number': 13} | {'precision': 0.5213675213675214, 'recall': 0.6039603960396039, 'f1': 0.5596330275229358, 'number': 202} | {'precision': 0.38028169014084506, 'recall': 0.627906976744186, 'f1': 0.4736842105263158, 'number': 43} | {'precision': 0.23809523809523808, 'recall': 0.2631578947368421, 'f1': 0.25, 'number': 19} | 0.4776 | 0.5776 | 0.5229 | 0.9504 |
|
57 |
+
| No log | 2.0 | 440 | 0.1513 | {'precision': 0.6, 'recall': 0.46153846153846156, 'f1': 0.5217391304347826, 'number': 13} | {'precision': 0.6008403361344538, 'recall': 0.7079207920792079, 'f1': 0.65, 'number': 202} | {'precision': 0.6538461538461539, 'recall': 0.7906976744186046, 'f1': 0.7157894736842104, 'number': 43} | {'precision': 0.3333333333333333, 'recall': 0.3157894736842105, 'f1': 0.3243243243243243, 'number': 19} | 0.5943 | 0.6823 | 0.6353 | 0.9564 |
|
58 |
+
| 0.1164 | 3.0 | 660 | 0.1569 | {'precision': 0.8888888888888888, 'recall': 0.6153846153846154, 'f1': 0.7272727272727274, 'number': 13} | {'precision': 0.6255506607929515, 'recall': 0.7029702970297029, 'f1': 0.662004662004662, 'number': 202} | {'precision': 0.723404255319149, 'recall': 0.7906976744186046, 'f1': 0.7555555555555555, 'number': 43} | {'precision': 0.3157894736842105, 'recall': 0.3157894736842105, 'f1': 0.3157894736842105, 'number': 19} | 0.6291 | 0.6859 | 0.6563 | 0.9587 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
- Transformers 4.42.4
|
64 |
+
- Pytorch 2.4.0+cu121
|
65 |
- Datasets 2.21.0
|
66 |
- Tokenizers 0.19.1
|