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
3cb0bd4
•
1 Parent(s): 7324473

add model

Browse files
Files changed (5) hide show
  1. README.md +10 -8
  2. pytorch_model.bin +1 -1
  3. runs/Oct19_04-59-04_37b645ac8054/1634619589.9841387/events.out.tfevents.1634619589.37b645ac8054.76.1 +3 -0
  4. runs/Oct19_04-59-04_37b645ac8054/events.out.tfevents.1634619589.37b645ac8054.76.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ model_index:
13
  metric:
14
  name: Bleu
15
  type: bleu
16
- value: 62.478
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -23,9 +23,9 @@ should probably proofread and complete it, then remove this comment. -->
23
 
24
  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.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.5744
27
- - Bleu: 62.478
28
- - Gen Len: 16.3807
29
 
30
  ## Model description
31
 
@@ -50,14 +50,16 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 1
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
59
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
60
- | 1.0649 | 1.0 | 247 | 0.5744 | 62.478 | 16.3807 |
 
 
61
 
62
 
63
  ### Framework versions
13
  metric:
14
  name: Bleu
15
  type: bleu
16
+ value: 76.0826
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
23
 
24
  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.
25
  It achieves the following results on the evaluation set:
26
+ - Loss: 0.4001
27
+ - Bleu: 76.0826
28
+ - Gen Len: 16.4264
29
 
30
  ## Model description
31
 
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 3
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
59
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
60
+ | 1.1048 | 1.0 | 247 | 0.5843 | 62.1912 | 16.2467 |
61
+ | 0.487 | 2.0 | 494 | 0.4414 | 71.5439 | 16.4904 |
62
+ | 0.2689 | 3.0 | 741 | 0.4001 | 76.0826 | 16.4264 |
63
 
64
 
65
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e105d78040cafc9bfc50d50b7aff4730f1d5f64a1d6e617278f3cf8f77da787
3
  size 301227653
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb82e3de7af4474ee706c7e78fb375091642643b1c1db9371ad1a9eee1d24d7
3
  size 301227653
runs/Oct19_04-59-04_37b645ac8054/1634619589.9841387/events.out.tfevents.1634619589.37b645ac8054.76.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281bcd65294a806797897c1b4550d3f43838932e82f2f11da35670e8e2947a65
3
+ size 4339
runs/Oct19_04-59-04_37b645ac8054/events.out.tfevents.1634619589.37b645ac8054.76.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f112145a8875ed978e3ca6c8fcbad5ee92322c1f7ed2cf59a131c9bb46bd4437
3
+ size 5670
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2fb731ace8c548f5efd7a121bcb4027b8fb5c3339d25efa5e9a806febc519b7
3
  size 2735
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4779605ea025bf543f14f9cdae14465f438ce73f27ff7c74720f7c6853c8194b
3
  size 2735