gozu888 commited on
Commit
5f561ab
1 Parent(s): 7da1aae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -13
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
 
16
  This model is a fine-tuned version of VietAI/envit5-translation on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set:
17
 
18
- - Loss: 0.1988
19
  - BLEU: 34.46
20
 
21
  ## Model Details
@@ -33,18 +33,10 @@ The following hyperparameters were used during training:
33
  - Repo: [simpleT5](https://github.com/Shivanandroy/simpleT5)
34
  - Dataset: [mt_eng_vietnamese](https://huggingface.co/datasets/mt_eng_vietnamese) + custom (~40%)
35
  ```python
36
- model.train(
37
- train_df=train_df,
38
- eval_df=test_df,
39
- source_max_token_len=128,
40
- target_max_token_len=128,
41
- batch_size=32,
42
- max_epochs=15,
43
- use_gpu=True,
44
- save_only_last_epoch=True,
45
- precision=16,
46
- dataloader_num_workers=4
47
- )
48
  ```
49
  ### Examples
50
 
 
15
 
16
  This model is a fine-tuned version of VietAI/envit5-translation on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set:
17
 
18
+ - Val Loss: 0.8422
19
  - BLEU: 34.46
20
 
21
  ## Model Details
 
33
  - Repo: [simpleT5](https://github.com/Shivanandroy/simpleT5)
34
  - Dataset: [mt_eng_vietnamese](https://huggingface.co/datasets/mt_eng_vietnamese) + custom (~40%)
35
  ```python
36
+ source_max_token_len=128
37
+ target_max_token_len=128
38
+ batch_size=32
39
+ max_epochs=8
 
 
 
 
 
 
 
 
40
  ```
41
  ### Examples
42