Hugging Face's logo

FiveC
/
za_zh_sc

Transformers
Safetensors
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
FiveC commited on
Commit
cb4f8db
·
verified ·
1 Parent(s): f932c2c

End of training

Browse files
Files changed (2) hide show
  1. README.md +5 -6
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.6823
21
- - Sacrebleu: 6.0325
22
 
23
  ## Model description
24
 
@@ -43,16 +43,15 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
- - num_epochs: 3
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
- | 2.4359 | 1.0 | 309 | 2.9542 | 3.4303 |
54
- | 1.5757 | 2.0 | 618 | 2.7130 | 4.8701 |
55
- | 1.2767 | 3.0 | 927 | 2.6823 | 6.0325 |
56
 
57
 
58
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.9950
21
+ - Sacrebleu: 4.4405
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 2
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 2.5108 | 1.0 | 309 | 2.9950 | 4.4405 |
54
+ | 1.7678 | 2.0 | 618 | 2.8134 | 3.4752 |
 
55
 
56
 
57
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8c993a3baf7a1c2f566869054bbc3fea35b85db960e122d8158e031ef54fe0
3
  size 2444582788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e7cc73ae9b3435c2455575f9d3217bdf54f799f014084d890f3f42b524e902
3
  size 2444582788