add model
Browse files
README.md
CHANGED
@@ -1,18 +1,12 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
-
metrics:
|
5 |
-
- bleu
|
6 |
model_index:
|
7 |
- name: opus-mt-ja-en-finetuned-ja-to-en_test
|
8 |
results:
|
9 |
- task:
|
10 |
name: Sequence-to-sequence Language Modeling
|
11 |
type: text2text-generation
|
12 |
-
metric:
|
13 |
-
name: Bleu
|
14 |
-
type: bleu
|
15 |
-
value: 27.3816
|
16 |
---
|
17 |
|
18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -21,10 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
# opus-mt-ja-en-finetuned-ja-to-en_test
|
22 |
|
23 |
This model is a fine-tuned version of [Edomonndo/opus-mt-ja-en-finetuned-ja-to-en_test](https://huggingface.co/Edomonndo/opus-mt-ja-en-finetuned-ja-to-en_test) on an unkown dataset.
|
24 |
-
It achieves the following results on the evaluation set:
|
25 |
-
- Loss: 3.1649
|
26 |
-
- Bleu: 27.3816
|
27 |
-
- Gen Len: 11.2584
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -49,16 +39,14 @@ The following hyperparameters were used during training:
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
- mixed_precision_training: Native AMP
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
59 |
-
| No log | 1.0 | 20 | 3.
|
60 |
-
| No log | 2.0 | 40 | 3.1899 | 26.5309 | 10.618 |
|
61 |
-
| No log | 3.0 | 60 | 3.1649 | 27.3816 | 11.2584 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
model_index:
|
5 |
- name: opus-mt-ja-en-finetuned-ja-to-en_test
|
6 |
results:
|
7 |
- task:
|
8 |
name: Sequence-to-sequence Language Modeling
|
9 |
type: text2text-generation
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
15 |
# opus-mt-ja-en-finetuned-ja-to-en_test
|
16 |
|
17 |
This model is a fine-tuned version of [Edomonndo/opus-mt-ja-en-finetuned-ja-to-en_test](https://huggingface.co/Edomonndo/opus-mt-ja-en-finetuned-ja-to-en_test) on an unkown dataset.
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 1
|
43 |
- mixed_precision_training: Native AMP
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
49 |
+
| No log | 1.0 | 20 | 3.2331 | 26.2316 | 11.0674 |
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 301227653
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:455825cfb06edd8842f2d71994df9c77c2ee05bcf20f4383752c0233319cfb80
|
3 |
size 301227653
|
runs/Jul27_14-25-36_0c83a5e99d28/1627395950.3402424/events.out.tfevents.1627395950.0c83a5e99d28.62.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eecbc6faf008e4af7bac495c74db3f39133088d00507d1266d453c50a2b67199
|
3 |
+
size 4339
|
runs/Jul27_14-25-36_0c83a5e99d28/events.out.tfevents.1627395950.0c83a5e99d28.62.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:542bc8cc85eddff1090e8792c86da31c24f58192d0a622e7deadf04c4a300413
|
3 |
+
size 4491
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2735
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:788773284a13544570cd87723ee7bb5f296e521ce6c2c3df2856cd9c3d02077a
|
3 |
size 2735
|