Hugging Face's logo

NIRVLab
/
ViEde

Transformers
Safetensors
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
HeyDunaX commited on
Commit
303b785
·
verified ·
1 Parent(s): 79da11b

End of training

Browse files
Files changed (2) hide show
  1. README.md +8 -7
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [NIRVLab/bartede](https://huggingface.co/NIRVLab/bartede) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5526
22
- - Bleu: 24.22
23
- - Chrf++: 47.9444
24
 
25
  ## Model description
26
 
@@ -45,16 +45,17 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - num_epochs: 3
 
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf++ |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
55
- | 0.263 | 1.0 | 2080 | 0.4947 | 22.3815 | 46.1506 |
56
- | 0.1502 | 2.0 | 4160 | 0.5381 | 23.9937 | 47.7224 |
57
- | 0.1249 | 3.0 | 6240 | 0.5526 | 24.22 | 47.9444 |
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [NIRVLab/bartede](https://huggingface.co/NIRVLab/bartede) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4809
22
+ - Bleu: 22.833
23
+ - Chrf++: 46.2491
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.06
49
+ - num_epochs: 5
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf++ |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
56
+ | 0.273 | 1.0 | 2080 | 0.4809 | 22.833 | 46.2491 |
57
+ | 0.1331 | 2.0 | 4160 | 0.5284 | 24.6028 | 48.483 |
58
+ | 0.0964 | 3.0 | 6240 | 0.5543 | 25.6692 | 49.2306 |
59
 
60
 
61
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9f5ac6bf7c3a254e3eb21c54ffc12dd334af11c0a9fb39068a6fee7d366986b
3
  size 1583480280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037d9d37c3bd93610a63fb6c20284c2929de4822d827faa7f9afca556514d6ed
3
  size 1583480280