Hugging Face's logo

ezzini
/
marian-finetuned-mcwc-es-to-en

Text2Text Generation
Transformers
TensorFlow
marian
generated_from_keras_callback
Inference Endpoints
Model card Files Community
ezzini commited on
Commit
1128a18
·
1 Parent(s): c4d89df

Training in progress epoch 2

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-en](https://huggingface.co/Helsinki-NLP/opus-mt-es-en) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.6781
19
- - Validation Loss: 0.7633
20
- - Epoch: 1
21
 
22
  ## Model description
23
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
45
  |:----------:|:---------------:|:-----:|
46
  | 0.9297 | 0.7942 | 0 |
47
  | 0.6781 | 0.7633 | 1 |
 
48
 
49
 
50
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-en](https://huggingface.co/Helsinki-NLP/opus-mt-es-en) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.5858
19
+ - Validation Loss: 0.7591
20
+ - Epoch: 2
21
 
22
  ## Model description
23
 
 
45
  |:----------:|:---------------:|:-----:|
46
  | 0.9297 | 0.7942 | 0 |
47
  | 0.6781 | 0.7633 | 1 |
48
+ | 0.5858 | 0.7591 | 2 |
49
 
50
 
51
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a41a595376651d11e9319c0363befb13e9c4363cc66b73ada6964ba1f5ff8507
3
  size 312320596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ef0a73d88266fd53e63b624d4d3a0a1dde287c5ecf3f59e473a54c587a42f8b
3
  size 312320596