Hugging Face's logo

Edomonndo
/
opus-mt-ja-en-finetuned-ja-to-en_test

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Edomonndo commited on
Commit
e037b67
•
1 Parent(s): cdf9ae2

add model

Browse files
Files changed (5) hide show
  1. README.md +6 -8
  2. pytorch_model.bin +1 -1
  3. runs/Sep07_00-34-39_245528ade5de/1630974928.905991/events.out.tfevents.1630974928.245528ade5de.74.1 +3 -0
  4. runs/Sep07_00-34-39_245528ade5de/events.out.tfevents.1630974928.245528ade5de.74.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ model_index:
12
  metric:
13
  name: Bleu
14
  type: bleu
15
- value: 31.9359
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,9 +22,9 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ja-en](https://huggingface.co/Helsinki-NLP/opus-mt-ja-en) on an unkown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 2.1907
26
- - Bleu: 31.9359
27
- - Gen Len: 12.7528
28
 
29
  ## Model description
30
 
@@ -49,16 +49,14 @@ 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: 3
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
59
- | 2.8569 | 1.0 | 20 | 2.4347 | 25.1308 | 11.5618 |
60
- | 1.2535 | 2.0 | 40 | 2.2551 | 30.7991 | 12.0562 |
61
- | 0.7096 | 3.0 | 60 | 2.1907 | 31.9359 | 12.7528 |
62
 
63
 
64
  ### Framework versions
 
12
  metric:
13
  name: Bleu
14
  type: bleu
15
+ value: 62.9394
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
22
 
23
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ja-en](https://huggingface.co/Helsinki-NLP/opus-mt-ja-en) on an unkown dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 0.5724
26
+ - Bleu: 62.9394
27
+ - Gen Len: 16.3066
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 1
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
59
+ | 0.6403 | 1.0 | 493 | 0.5724 | 62.9394 | 16.3066 |
 
 
60
 
61
 
62
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:760071bc36bccd7b81cc8e24657186ad944ee0b75601ad419a02d854ba5875a0
3
  size 301227653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7453241c6c9c02ebbcce016954ad14f98531abd20be81948d7e623ed199596ce
3
  size 301227653
runs/Sep07_00-34-39_245528ade5de/1630974928.905991/events.out.tfevents.1630974928.245528ade5de.74.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f4082520fe3e793102e0aa170e48ef8b12c0f35ea9139b066131db24e13340
3
+ size 4339
runs/Sep07_00-34-39_245528ade5de/events.out.tfevents.1630974928.245528ade5de.74.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698fc31d91c7c9dcd9d4f0e855fc98f51e8e0a384cfafefa84404ed5b6d8bc00
3
+ size 8208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cdb1f80f86a993c650d6b0740049a5327ce06589f9ac23f931aa04632702393
3
  size 2735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9317e52cc818b03c9160837f8302592d09c05e7f7f413e87ae272b90260ed1
3
  size 2735