Update README.md
Browse files
README.md
CHANGED
@@ -11,7 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# ai-club-inductions-21-nlp-ELECTRA-base-squad
|
13 |
|
14 |
-
This model
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -19,18 +19,21 @@ More information needed
|
|
19 |
|
20 |
## Intended uses & limitations
|
21 |
|
22 |
-
|
23 |
|
24 |
## Training and evaluation data
|
25 |
|
26 |
-
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
### Training hyperparameters
|
31 |
|
32 |
The following hyperparameters were used during training:
|
|
|
|
|
33 |
- learning_rate: 2e-05
|
|
|
34 |
- train_batch_size: 16
|
35 |
- eval_batch_size: 16
|
36 |
- seed: 42
|
|
|
11 |
|
12 |
# ai-club-inductions-21-nlp-ELECTRA-base-squad
|
13 |
|
14 |
+
This model is the deepset/electra-base-squad2 pre-trained model trained on data from AI Inductions 21 NLP competition (https://www.kaggle.com/c/ai-inductions-21-nlp) for extractive QA.
|
15 |
|
16 |
## Model description
|
17 |
|
|
|
19 |
|
20 |
## Intended uses & limitations
|
21 |
|
22 |
+
AI Inductions 21 NLP competition
|
23 |
|
24 |
## Training and evaluation data
|
25 |
|
26 |
+
AI Inductions 21 NLP competition data
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
### Training hyperparameters
|
31 |
|
32 |
The following hyperparameters were used during training:
|
33 |
+
- max_length = 512
|
34 |
+
- doc_stride = 384
|
35 |
- learning_rate: 2e-05
|
36 |
+
- weight_decay=0.01
|
37 |
- train_batch_size: 16
|
38 |
- eval_batch_size: 16
|
39 |
- seed: 42
|