Update README.md
Browse files
README.md
CHANGED
@@ -16,14 +16,15 @@ datasets:
|
|
16 |
## deberta-v3-large-snli_mnli_fever_anli_R1_R2_R3-nli
|
17 |
|
18 |
#### Datasets
|
19 |
-
Based on microsoft/deberta-v3-large, this model was trained on the snli-v1.0, multi-nli-1.0, nli-fever and anli-1.0-r1/anli-1.0-r2/anli-1.0-r3 datasets, with the training weights of 1,1,1,10,20,10 respectively.
|
|
|
20 |
|
21 |
#### Hyperparameters
|
22 |
learning_rate: 1e-5
|
23 |
max_length: 156
|
24 |
-
batch_size: 16
|
25 |
-
warmup_ratio: 0.1
|
26 |
-
weight_decay: 0.0
|
27 |
num_epochs: 2
|
28 |
|
29 |
#### dev_results
|
|
|
16 |
## deberta-v3-large-snli_mnli_fever_anli_R1_R2_R3-nli
|
17 |
|
18 |
#### Datasets
|
19 |
+
Based on microsoft/deberta-v3-large, this model was trained on the snli-v1.0, multi-nli-1.0, nli-fever and anli-1.0-r1/anli-1.0-r2/anli-1.0-r3 datasets, with the training weights of 1,1,1,10,20,10 respectively.
|
20 |
+
The training codes are mostly referenced from: https://github.com/facebookresearch/anli
|
21 |
|
22 |
#### Hyperparameters
|
23 |
learning_rate: 1e-5
|
24 |
max_length: 156
|
25 |
+
batch_size: 16
|
26 |
+
warmup_ratio: 0.1
|
27 |
+
weight_decay: 0.0
|
28 |
num_epochs: 2
|
29 |
|
30 |
#### dev_results
|