Commit
•
064a9b2
1
Parent(s):
b257742
Shree Ganeshay Namah, NER-POS Training with seqeval metrics complete
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -25,16 +25,16 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
-
value: 0.
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
-
value: 0.
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
-
value: 0.
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
42 |
|
43 |
# pos-ner-tagging-v2
|
44 |
|
45 |
-
This model is a fine-tuned version of [
|
46 |
It achieves the following results on the evaluation set:
|
47 |
-
- Loss: 0.
|
48 |
-
- Precision: 0.
|
49 |
-
- Recall: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Accuracy: 0.
|
52 |
|
53 |
## Model description
|
54 |
|
@@ -73,13 +73,28 @@ The following hyperparameters were used during training:
|
|
73 |
- seed: 42
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
76 |
-
- num_epochs:
|
77 |
|
78 |
### Training results
|
79 |
|
80 |
-
| Training Loss | Epoch | Step
|
81 |
-
|
82 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
|
84 |
|
85 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: om-ashish-soni/pos-ner-tagging-v2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
+
value: 0.9393653920267203
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
+
value: 0.9408358887483113
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
+
value: 0.9401000653531749
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9270324365691411
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
|
43 |
# pos-ner-tagging-v2
|
44 |
|
45 |
+
This model is a fine-tuned version of [om-ashish-soni/pos-ner-tagging-v2](https://huggingface.co/om-ashish-soni/pos-ner-tagging-v2) on the conll2003 dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.6442
|
48 |
+
- Precision: 0.9394
|
49 |
+
- Recall: 0.9408
|
50 |
+
- F1: 0.9401
|
51 |
+
- Accuracy: 0.9270
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
73 |
- seed: 42
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
76 |
+
- num_epochs: 16
|
77 |
|
78 |
### Training results
|
79 |
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| 0.3297 | 1.0 | 1756 | 0.4190 | 0.9189 | 0.9231 | 0.9210 | 0.9051 |
|
83 |
+
| 0.2521 | 2.0 | 3512 | 0.3836 | 0.9210 | 0.9300 | 0.9255 | 0.9114 |
|
84 |
+
| 0.1932 | 3.0 | 5268 | 0.4155 | 0.9295 | 0.9338 | 0.9316 | 0.9183 |
|
85 |
+
| 0.1325 | 4.0 | 7024 | 0.3969 | 0.9328 | 0.9356 | 0.9342 | 0.9211 |
|
86 |
+
| 0.0973 | 5.0 | 8780 | 0.4247 | 0.9332 | 0.9367 | 0.9349 | 0.9222 |
|
87 |
+
| 0.0799 | 6.0 | 10536 | 0.4606 | 0.9338 | 0.9374 | 0.9356 | 0.9229 |
|
88 |
+
| 0.0554 | 7.0 | 12292 | 0.4836 | 0.9333 | 0.9379 | 0.9356 | 0.9239 |
|
89 |
+
| 0.0415 | 8.0 | 14048 | 0.5271 | 0.9361 | 0.9391 | 0.9376 | 0.9245 |
|
90 |
+
| 0.0285 | 9.0 | 15804 | 0.5363 | 0.9366 | 0.9397 | 0.9381 | 0.9253 |
|
91 |
+
| 0.022 | 10.0 | 17560 | 0.5653 | 0.9377 | 0.9396 | 0.9387 | 0.9258 |
|
92 |
+
| 0.0146 | 11.0 | 19316 | 0.5962 | 0.9374 | 0.9400 | 0.9387 | 0.9259 |
|
93 |
+
| 0.0121 | 12.0 | 21072 | 0.6061 | 0.9385 | 0.9401 | 0.9393 | 0.9266 |
|
94 |
+
| 0.0085 | 13.0 | 22828 | 0.6263 | 0.9384 | 0.9403 | 0.9394 | 0.9261 |
|
95 |
+
| 0.0062 | 14.0 | 24584 | 0.6365 | 0.9381 | 0.9399 | 0.9390 | 0.9259 |
|
96 |
+
| 0.0053 | 15.0 | 26340 | 0.6386 | 0.9384 | 0.9402 | 0.9393 | 0.9264 |
|
97 |
+
| 0.0042 | 16.0 | 28096 | 0.6442 | 0.9394 | 0.9408 | 0.9401 | 0.9270 |
|
98 |
|
99 |
|
100 |
### Framework versions
|