dangkhoa99
commited on
Commit
•
cee52cb
1
Parent(s):
50f034b
Update README.md
Browse files
README.md
CHANGED
@@ -5,8 +5,10 @@ tags:
|
|
5 |
datasets:
|
6 |
- squad_v2
|
7 |
model-index:
|
8 |
-
- name: roberta-base-finetuned-squad-v2
|
9 |
results: []
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,6 +36,7 @@ More information needed
|
|
34 |
|
35 |
### Training hyperparameters
|
36 |
|
|
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 2e-05
|
39 |
- train_batch_size: 16
|
@@ -42,19 +45,44 @@ The following hyperparameters were used during training:
|
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
- num_epochs: 3
|
|
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
| 0.8796 | 1.0 | 8239 | 0.8010 |
|
51 |
| 0.6474 | 2.0 | 16478 | 0.8260 |
|
52 |
| 0.5056 | 3.0 | 24717 | 0.9173 |
|
53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.30.2
|
58 |
- Pytorch 2.0.1+cu118
|
59 |
- Datasets 2.13.1
|
60 |
-
- Tokenizers 0.13.3
|
|
|
5 |
datasets:
|
6 |
- squad_v2
|
7 |
model-index:
|
8 |
+
- name: dangkhoa99/roberta-base-finetuned-squad-v2
|
9 |
results: []
|
10 |
+
language:
|
11 |
+
- en
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
36 |
|
37 |
### Training hyperparameters
|
38 |
|
39 |
+
```
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 2e-05
|
42 |
- train_batch_size: 16
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- num_epochs: 3
|
48 |
+
```
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
```
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:-----:|:---------------:|
|
55 |
| 0.8796 | 1.0 | 8239 | 0.8010 |
|
56 |
| 0.6474 | 2.0 | 16478 | 0.8260 |
|
57 |
| 0.5056 | 3.0 | 24717 | 0.9173 |
|
58 |
+
```
|
59 |
+
|
60 |
+
### Performance
|
61 |
+
Evaluated on the SQuAD 2.0 dev set with the [QuestionAnsweringEvaluator](https://huggingface.co/docs/evaluate/v0.4.0/en/package_reference/evaluator_classes#evaluate.QuestionAnsweringEvaluator)
|
62 |
+
|
63 |
+
```
|
64 |
+
'exact': 80.28299503074201
|
65 |
+
'f1': 83.54728996177538
|
66 |
+
|
67 |
+
'total': 11873
|
68 |
+
'HasAns_exact': 78.77867746288798
|
69 |
+
'HasAns_f1': 85.31662849462904
|
70 |
+
'HasAns_total': 5928
|
71 |
+
'NoAns_exact': 81.7830109335576
|
72 |
+
'NoAns_f1': 81.7830109335576
|
73 |
+
'NoAns_total': 5945
|
74 |
+
'best_exact': 80.28299503074201
|
75 |
+
'best_exact_thresh': 0.9989414811134338
|
76 |
+
'best_f1': 83.54728996177576
|
77 |
+
'best_f1_thresh': 0.9989414811134338
|
78 |
+
'total_time_in_seconds': 220.1965392809998
|
79 |
+
'samples_per_second': 53.92001181657305
|
80 |
+
'latency_in_seconds': 0.01854599000092645
|
81 |
+
```
|
82 |
|
83 |
### Framework versions
|
84 |
|
85 |
- Transformers 4.30.2
|
86 |
- Pytorch 2.0.1+cu118
|
87 |
- Datasets 2.13.1
|
88 |
+
- Tokenizers 0.13.3
|