Commit
•
56d11a0
1
Parent(s):
081cba9
update model card README.md
Browse files- tiny-mbart-quechua/README.md +14 -0
tiny-mbart-quechua/README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
tags:
|
3 |
- simplification
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: tiny-mbart-quechua
|
7 |
results: []
|
@@ -13,6 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
# tiny-mbart-quechua
|
14 |
|
15 |
This model is a fine-tuned version of [sshleifer/tiny-mbart](https://huggingface.co/sshleifer/tiny-mbart) on an unknown dataset.
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -39,6 +45,14 @@ The following hyperparameters were used during training:
|
|
39 |
- lr_scheduler_type: linear
|
40 |
- num_epochs: 2
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
### Framework versions
|
43 |
|
44 |
- Transformers 4.26.1
|
|
|
2 |
tags:
|
3 |
- simplification
|
4 |
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
model-index:
|
8 |
- name: tiny-mbart-quechua
|
9 |
results: []
|
|
|
15 |
# tiny-mbart-quechua
|
16 |
|
17 |
This model is a fine-tuned version of [sshleifer/tiny-mbart](https://huggingface.co/sshleifer/tiny-mbart) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 5.8454
|
20 |
+
- Bleu: 0.0
|
21 |
+
- Gen Len: 20.0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
45 |
- lr_scheduler_type: linear
|
46 |
- num_epochs: 2
|
47 |
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:----:|:-------:|
|
52 |
+
| 5.9674 | 1.0 | 25687 | 5.9599 | 0.0 | 20.0 |
|
53 |
+
| 5.8352 | 2.0 | 51374 | 5.8454 | 0.0 | 20.0 |
|
54 |
+
|
55 |
+
|
56 |
### Framework versions
|
57 |
|
58 |
- Transformers 4.26.1
|