add hparams
Browse files- README.md +4 -2
- hparams.yaml +28 -0
README.md
CHANGED
@@ -100,9 +100,11 @@ base_model:
|
|
100 |
- FacebookAI/xlm-roberta-large
|
101 |
---
|
102 |
|
|
|
|
|
103 |
This is a source-only COMET model used for efficient evaluation subset selection.
|
104 |
-
It is not compatible with the upstream [github.com/Unbabel/COMET/](https://github.com/Unbabel/COMET/) and to run it you have to install [github.com/zouharvi/
|
105 |
|
106 |
The primary use of this model is from the [subset2evaluate](https://github.com/zouharvi/subset2evaluate) package.
|
107 |
|
108 |
-
Further
|
|
|
100 |
- FacebookAI/xlm-roberta-large
|
101 |
---
|
102 |
|
103 |
+
# PreCOMET-diversity
|
104 |
+
|
105 |
This is a source-only COMET model used for efficient evaluation subset selection.
|
106 |
+
It is not compatible with the upstream [github.com/Unbabel/COMET/](https://github.com/Unbabel/COMET/) and to run it you have to install [github.com/zouharvi/PreCOMET](https://github.com/zouharvi/PreCOMET).
|
107 |
|
108 |
The primary use of this model is from the [subset2evaluate](https://github.com/zouharvi/subset2evaluate) package.
|
109 |
|
110 |
+
Further description TODO.
|
hparams.yaml
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
nr_frozen_epochs: 0.3
|
2 |
+
keep_embeddings_frozen: true
|
3 |
+
optimizer: AdamW
|
4 |
+
warmup_steps: 0
|
5 |
+
encoder_learning_rate: 1.0e-06
|
6 |
+
learning_rate: 1.5e-05
|
7 |
+
layerwise_decay: 0.95
|
8 |
+
encoder_model: XLM-RoBERTa
|
9 |
+
pretrained_model: xlm-roberta-large
|
10 |
+
pool: avg
|
11 |
+
layer: mix
|
12 |
+
layer_transformation: sparsemax
|
13 |
+
layer_norm: false
|
14 |
+
loss: mse
|
15 |
+
dropout: 0.1
|
16 |
+
batch_size: 16
|
17 |
+
train_data:
|
18 |
+
- data/csv/train_div.csv
|
19 |
+
validation_data:
|
20 |
+
- data/csv/dev_div.csv
|
21 |
+
class_identifier: hypothesisless_regression_metric
|
22 |
+
load_pretrained_weights: true
|
23 |
+
local_files_only: false
|
24 |
+
hidden_sizes:
|
25 |
+
- 2048
|
26 |
+
- 1024
|
27 |
+
activations: Tanh
|
28 |
+
final_activation: null
|