Sancha commited on
Commit
401c476
1 Parent(s): ba8aa26

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -6
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Bleu
21
  type: bleu
22
- value: 1.2607
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wmt19 dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 3.5004
33
- - Bleu: 1.2607
34
- - Gen Len: 17.1943
35
 
36
  ## Model description
37
 
@@ -57,13 +57,14 @@ The following hyperparameters were used during training:
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
  - num_epochs: 2
 
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
64
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
65
- | 3.3914 | 1.0 | 6250 | 3.5255 | 1.2017 | 17.1033 |
66
- | 3.3221 | 2.0 | 12500 | 3.5004 | 1.2607 | 17.1943 |
67
 
68
 
69
  ### Framework versions
19
  metrics:
20
  - name: Bleu
21
  type: bleu
22
+ value: 1.2541
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
 
30
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wmt19 dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 3.5185
33
+ - Bleu: 1.2541
34
+ - Gen Len: 17.395
35
 
36
  ## Model description
37
 
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
  - num_epochs: 2
60
+ - mixed_precision_training: Native AMP
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
65
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
66
+ | 3.413 | 1.0 | 6250 | 3.5378 | 1.2291 | 17.4057 |
67
+ | 3.342 | 2.0 | 12500 | 3.5185 | 1.2541 | 17.395 |
68
 
69
 
70
  ### Framework versions