Training in progress epoch 2
Browse files- README.md +6 -5
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -16,11 +16,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Train Loss:
|
20 |
-
- Validation Loss: 3.
|
21 |
-
- Train Bleu: 0.
|
22 |
-
- Train Gen Len:
|
23 |
-
- Epoch:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
|
|
48 |
|:----------:|:---------------:|:----------:|:-------------:|:-----:|
|
49 |
| 3.2664 | 3.8681 | 0.5880 | 81.3419 | 0 |
|
50 |
| 3.1141 | 3.8693 | 0.6464 | 87.0342 | 1 |
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 2.9924
|
20 |
+
- Validation Loss: 3.8645
|
21 |
+
- Train Bleu: 0.6098
|
22 |
+
- Train Gen Len: 81.2051
|
23 |
+
- Epoch: 2
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
48 |
|:----------:|:---------------:|:----------:|:-------------:|:-----:|
|
49 |
| 3.2664 | 3.8681 | 0.5880 | 81.3419 | 0 |
|
50 |
| 3.1141 | 3.8693 | 0.6464 | 87.0342 | 1 |
|
51 |
+
| 2.9924 | 3.8645 | 0.6098 | 81.2051 | 2 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 312320596
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98c17080b9c2df5a5247e4a8d6db4eeea51fc311b374b0d4040004408a24f21c
|
3 |
size 312320596
|