update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- wnut_17
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: xlm-roberta-base-wnut2017-en
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
dataset:
|
19 |
+
name: wnut_17
|
20 |
+
type: wnut_17
|
21 |
+
config: wnut_17
|
22 |
+
split: validation
|
23 |
+
args: wnut_17
|
24 |
+
metrics:
|
25 |
+
- name: Precision
|
26 |
+
type: precision
|
27 |
+
value: 0.7219662058371735
|
28 |
+
- name: Recall
|
29 |
+
type: recall
|
30 |
+
value: 0.562200956937799
|
31 |
+
- name: F1
|
32 |
+
type: f1
|
33 |
+
value: 0.6321452589105581
|
34 |
+
- name: Accuracy
|
35 |
+
type: accuracy
|
36 |
+
value: 0.9589398080467807
|
37 |
+
---
|
38 |
+
|
39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
+
should probably proofread and complete it, then remove this comment. -->
|
41 |
+
|
42 |
+
# xlm-roberta-base-wnut2017-en
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the wnut_17 dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.2319
|
47 |
+
- Precision: 0.7220
|
48 |
+
- Recall: 0.5622
|
49 |
+
- F1: 0.6321
|
50 |
+
- Accuracy: 0.9589
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 2e-05
|
70 |
+
- train_batch_size: 32
|
71 |
+
- eval_batch_size: 32
|
72 |
+
- seed: 42
|
73 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
+
- lr_scheduler_type: linear
|
75 |
+
- num_epochs: 15
|
76 |
+
|
77 |
+
### Training results
|
78 |
+
|
79 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| No log | 1.0 | 107 | 0.2789 | 0.4679 | 0.3397 | 0.3936 | 0.9408 |
|
82 |
+
| No log | 2.0 | 214 | 0.2092 | 0.6875 | 0.5 | 0.5789 | 0.9518 |
|
83 |
+
| No log | 3.0 | 321 | 0.1968 | 0.6194 | 0.5431 | 0.5787 | 0.9567 |
|
84 |
+
| No log | 4.0 | 428 | 0.2172 | 0.7212 | 0.5383 | 0.6164 | 0.9586 |
|
85 |
+
| 0.1523 | 5.0 | 535 | 0.2319 | 0.7220 | 0.5622 | 0.6321 | 0.9589 |
|
86 |
+
| 0.1523 | 6.0 | 642 | 0.2023 | 0.6180 | 0.5514 | 0.5828 | 0.9577 |
|
87 |
+
| 0.1523 | 7.0 | 749 | 0.2494 | 0.6895 | 0.5419 | 0.6068 | 0.9589 |
|
88 |
+
| 0.1523 | 8.0 | 856 | 0.2844 | 0.7018 | 0.5263 | 0.6015 | 0.9578 |
|
89 |
+
| 0.1523 | 9.0 | 963 | 0.2568 | 0.6808 | 0.5562 | 0.6122 | 0.9592 |
|
90 |
+
| 0.0294 | 10.0 | 1070 | 0.2453 | 0.6718 | 0.5754 | 0.6198 | 0.9596 |
|
91 |
+
| 0.0294 | 11.0 | 1177 | 0.2538 | 0.6933 | 0.5706 | 0.6260 | 0.9600 |
|
92 |
+
| 0.0294 | 12.0 | 1284 | 0.2638 | 0.6865 | 0.5658 | 0.6203 | 0.9593 |
|
93 |
+
| 0.0294 | 13.0 | 1391 | 0.2744 | 0.6764 | 0.5526 | 0.6083 | 0.9587 |
|
94 |
+
| 0.0294 | 14.0 | 1498 | 0.2714 | 0.6812 | 0.5622 | 0.6160 | 0.9590 |
|
95 |
+
| 0.0135 | 15.0 | 1605 | 0.2724 | 0.6830 | 0.5670 | 0.6196 | 0.9593 |
|
96 |
+
|
97 |
+
|
98 |
+
### Framework versions
|
99 |
+
|
100 |
+
- Transformers 4.26.1
|
101 |
+
- Pytorch 1.13.1+cu116
|
102 |
+
- Datasets 2.9.0
|
103 |
+
- Tokenizers 0.13.2
|