aijadugar commited on
Commit
dc68d6d
·
verified ·
1 Parent(s): d86772e

Add Seq2Seq LSTM trained on Multi30K

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -7,7 +7,7 @@ language:
7
  library_name: pytorch
8
  pipeline_tag: translation
9
  tags:
10
- - pytorch
11
  - lstm
12
  - seq2seq
13
  - machine-translation
@@ -16,7 +16,7 @@ datasets:
16
  - bentrevett/multi30k
17
  ---
18
 
19
- # Seq2Seq RNN Translator (English -> German)
20
 
21
  A PyTorch Seq2Seq Encoder-Decoder LSTM trained from scratch on the Multi30k dataset.
22
 
@@ -49,10 +49,10 @@ A PyTorch Seq2Seq Encoder-Decoder LSTM trained from scratch on the Multi30k data
49
 
50
  | Metric | Value |
51
  |------|------:|
52
- | Train Loss | 3.57 |
53
- | Validation Loss | 5.35 |
54
- | Test Loss | 5.20 |
55
- | BLEU | 2.17 |
56
 
57
  ![](en_de_lstm_loss.png)
58
 
 
7
  library_name: pytorch
8
  pipeline_tag: translation
9
  tags:
10
+ - pytorchf
11
  - lstm
12
  - seq2seq
13
  - machine-translation
 
16
  - bentrevett/multi30k
17
  ---
18
 
19
+ # Seq2Seq LSTM Translator (English -> German)
20
 
21
  A PyTorch Seq2Seq Encoder-Decoder LSTM trained from scratch on the Multi30k dataset.
22
 
 
49
 
50
  | Metric | Value |
51
  |------|------:|
52
+ | Train Loss | 0.62 |
53
+ | Validation Loss | 5.55 |
54
+ | Test Loss | 3.79 |
55
+ | BLEU | 14.70 |
56
 
57
  ![](en_de_lstm_loss.png)
58