update model card README.md
Browse files
README.md
CHANGED
@@ -1,30 +1,12 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- en
|
4 |
-
- 'no'
|
5 |
license: apache-2.0
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- bible_para
|
10 |
-
metrics:
|
11 |
-
- bleu
|
12 |
model-index:
|
13 |
- name: flan-t5-small_en-no
|
14 |
-
results:
|
15 |
-
- task:
|
16 |
-
name: Translation
|
17 |
-
type: translation
|
18 |
-
dataset:
|
19 |
-
name: bible_para en-no
|
20 |
-
type: bible_para
|
21 |
-
config: en-no
|
22 |
-
split: train
|
23 |
-
args: en-no
|
24 |
-
metrics:
|
25 |
-
- name: Bleu
|
26 |
-
type: bleu
|
27 |
-
value: 0.0331
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,11 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
# flan-t5-small_en-no
|
34 |
|
35 |
-
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the bible_para
|
36 |
-
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 3.3171
|
38 |
-
- Bleu: 0.0331
|
39 |
-
- Gen Len: 124.5707
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -56,12 +34,12 @@ More information needed
|
|
56 |
|
57 |
The following hyperparameters were used during training:
|
58 |
- learning_rate: 5e-05
|
59 |
-
- train_batch_size:
|
60 |
-
- eval_batch_size:
|
61 |
- seed: 42
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
-
-
|
65 |
|
66 |
### Training results
|
67 |
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- bible_para
|
|
|
|
|
7 |
model-index:
|
8 |
- name: flan-t5-small_en-no
|
9 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
14 |
|
15 |
# flan-t5-small_en-no
|
16 |
|
17 |
+
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the bible_para dataset.
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 5e-05
|
37 |
+
- train_batch_size: 256
|
38 |
+
- eval_batch_size: 128
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 3.0
|
43 |
|
44 |
### Training results
|
45 |
|