Commit
•
3afe500
1
Parent(s):
9b9edc7
End of training
Browse files
README.md
CHANGED
@@ -2,26 +2,53 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
-
- name:
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
-
<!-- This model card has been generated automatically according to the information
|
12 |
-
probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
#
|
15 |
|
16 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
-
|
20 |
-
-
|
21 |
-
-
|
22 |
-
-
|
23 |
-
- Train Accuracy: 0.9469
|
24 |
-
- Epoch: 2
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -40,21 +67,25 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
-
|
44 |
-
-
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
-
|
|
49 |
-
|
50 |
-
|
|
51 |
-
| 0
|
52 |
-
| 0.1100 | 0.2607 | 0.5710 | 0.4378 | 0.4956 | 0.9469 | 2 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.35.2
|
58 |
-
-
|
59 |
- Datasets 2.15.0
|
60 |
- Tokenizers 0.15.0
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- wnut_17
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
model-index:
|
14 |
+
- name: my_awesome_wnut_model
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: wnut_17
|
21 |
+
type: wnut_17
|
22 |
+
config: wnut_17
|
23 |
+
split: test
|
24 |
+
args: wnut_17
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.578853046594982
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.29935125115848005
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.3946243127672571
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.9410884528237357
|
38 |
---
|
39 |
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
|
43 |
+
# my_awesome_wnut_model
|
44 |
|
45 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.2727
|
48 |
+
- Precision: 0.5789
|
49 |
+
- Recall: 0.2994
|
50 |
+
- F1: 0.3946
|
51 |
+
- Accuracy: 0.9411
|
|
|
|
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
67 |
### Training hyperparameters
|
68 |
|
69 |
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 2e-05
|
71 |
+
- train_batch_size: 16
|
72 |
+
- eval_batch_size: 16
|
73 |
+
- seed: 42
|
74 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
+
- lr_scheduler_type: linear
|
76 |
+
- num_epochs: 2
|
77 |
|
78 |
### Training results
|
79 |
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| No log | 1.0 | 213 | 0.2873 | 0.5128 | 0.2234 | 0.3112 | 0.9376 |
|
83 |
+
| No log | 2.0 | 426 | 0.2727 | 0.5789 | 0.2994 | 0.3946 | 0.9411 |
|
|
|
84 |
|
85 |
|
86 |
### Framework versions
|
87 |
|
88 |
- Transformers 4.35.2
|
89 |
+
- Pytorch 2.1.0+cu118
|
90 |
- Datasets 2.15.0
|
91 |
- Tokenizers 0.15.0
|