Commit
•
84d10e6
1
Parent(s):
0d44470
update model card README.md
Browse files
README.md
CHANGED
@@ -4,9 +4,22 @@ tags:
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- turkic_xwmt
|
|
|
|
|
7 |
model-index:
|
8 |
- name: opus-mt-tr-en-finetuned-az-to-en
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,6 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# opus-mt-tr-en-finetuned-az-to-en
|
16 |
|
17 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tr-en](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en) on the turkic_xwmt dataset.
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,14 +56,23 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
43 |
- mixed_precision_training: Native AMP
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu
|
48 |
-
|
49 |
-
| No log | 1.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- turkic_xwmt
|
7 |
+
metrics:
|
8 |
+
- bleu
|
9 |
model-index:
|
10 |
- name: opus-mt-tr-en-finetuned-az-to-en
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: turkic_xwmt
|
17 |
+
type: turkic_xwmt
|
18 |
+
args: az-en
|
19 |
+
metrics:
|
20 |
+
- name: Bleu
|
21 |
+
type: bleu
|
22 |
+
value: 0.0002
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
28 |
# opus-mt-tr-en-finetuned-az-to-en
|
29 |
|
30 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tr-en](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en) on the turkic_xwmt dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: nan
|
33 |
+
- Bleu: 0.0002
|
34 |
+
- Gen Len: 511.0
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
56 |
- seed: 42
|
57 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
- lr_scheduler_type: linear
|
59 |
+
- num_epochs: 10
|
60 |
- mixed_precision_training: Native AMP
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
66 |
+
| No log | 1.0 | 38 | nan | 0.0002 | 511.0 |
|
67 |
+
| No log | 2.0 | 76 | nan | 0.0002 | 511.0 |
|
68 |
+
| No log | 3.0 | 114 | nan | 0.0002 | 511.0 |
|
69 |
+
| No log | 4.0 | 152 | nan | 0.0002 | 511.0 |
|
70 |
+
| No log | 5.0 | 190 | nan | 0.0002 | 511.0 |
|
71 |
+
| No log | 6.0 | 228 | nan | 0.0002 | 511.0 |
|
72 |
+
| No log | 7.0 | 266 | nan | 0.0002 | 511.0 |
|
73 |
+
| No log | 8.0 | 304 | nan | 0.0002 | 511.0 |
|
74 |
+
| No log | 9.0 | 342 | nan | 0.0002 | 511.0 |
|
75 |
+
| No log | 10.0 | 380 | nan | 0.0002 | 511.0 |
|
76 |
|
77 |
|
78 |
### Framework versions
|