Commit
•
5e9b544
1
Parent(s):
40cbc54
update model card README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,6 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- es
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- jorgeortizfuentes/spanish_nominal_groups_conll2003
|
8 |
model-index:
|
9 |
- name: nominal-groups-recognition-bert-base-spanish-wwm-cased
|
10 |
results: []
|
@@ -15,17 +11,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# nominal-groups-recognition-bert-base-spanish-wwm-cased
|
17 |
|
18 |
-
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Ng Precision: 0.
|
22 |
-
- Ng Recall: 0.
|
23 |
-
- Ng F1: 0.
|
24 |
- Ng Number: 3198
|
25 |
-
- Overall Precision: 0.
|
26 |
-
- Overall Recall: 0.
|
27 |
-
- Overall F1: 0.
|
28 |
-
- Overall Accuracy: 0.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -45,8 +41,8 @@ More information needed
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 2e-05
|
48 |
-
- train_batch_size:
|
49 |
-
- eval_batch_size:
|
50 |
- seed: 13
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
@@ -56,16 +52,16 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Ng Precision | Ng Recall | Ng F1 | Ng Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:---------:|:------:|:---------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
- Transformers 4.30.2
|
69 |
-
- Pytorch 2.0.1+
|
70 |
- Datasets 2.13.1
|
71 |
- Tokenizers 0.13.3
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
model-index:
|
5 |
- name: nominal-groups-recognition-bert-base-spanish-wwm-cased
|
6 |
results: []
|
|
|
11 |
|
12 |
# nominal-groups-recognition-bert-base-spanish-wwm-cased
|
13 |
|
14 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.3568
|
17 |
+
- Ng Precision: 0.7280
|
18 |
+
- Ng Recall: 0.7767
|
19 |
+
- Ng F1: 0.7516
|
20 |
- Ng Number: 3198
|
21 |
+
- Overall Precision: 0.7280
|
22 |
+
- Overall Recall: 0.7767
|
23 |
+
- Overall F1: 0.7516
|
24 |
+
- Overall Accuracy: 0.8992
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
- learning_rate: 2e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
- seed: 13
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Ng Precision | Ng Recall | Ng F1 | Ng Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:---------:|:------:|:---------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
55 |
+
| 0.3955 | 1.0 | 228 | 0.2778 | 0.7129 | 0.7492 | 0.7306 | 3198 | 0.7129 | 0.7492 | 0.7306 | 0.8924 |
|
56 |
+
| 0.2186 | 2.0 | 456 | 0.2763 | 0.7318 | 0.7711 | 0.7509 | 3198 | 0.7318 | 0.7711 | 0.7509 | 0.8990 |
|
57 |
+
| 0.1586 | 3.0 | 684 | 0.2960 | 0.7274 | 0.7733 | 0.7496 | 3198 | 0.7274 | 0.7733 | 0.7496 | 0.8992 |
|
58 |
+
| 0.119 | 4.0 | 912 | 0.3330 | 0.7283 | 0.7727 | 0.7498 | 3198 | 0.7283 | 0.7727 | 0.7498 | 0.8982 |
|
59 |
+
| 0.0943 | 5.0 | 1140 | 0.3568 | 0.7280 | 0.7767 | 0.7516 | 3198 | 0.7280 | 0.7767 | 0.7516 | 0.8992 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
- Transformers 4.30.2
|
65 |
+
- Pytorch 2.0.1+cu118
|
66 |
- Datasets 2.13.1
|
67 |
- Tokenizers 0.13.3
|