Hugging Face's logo

NIRVLab
/
bartede

Transformers
Safetensors
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
HeyDunaX commited on
Commit
c13b0e9
·
verified ·
1 Parent(s): eaa5c6d

End of training

Browse files
Files changed (2) hide show
  1. README.md +15 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5731
20
 
21
  ## Model description
22
 
@@ -35,12 +35,15 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 2e-05
39
- - train_batch_size: 64
40
- - eval_batch_size: 16
41
  - seed: 42
 
 
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
 
44
  - num_epochs: 15
45
  - mixed_precision_training: Native AMP
46
 
@@ -48,21 +51,14 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 158 | 0.8921 |
52
- | No log | 2.0 | 316 | 0.7830 |
53
- | No log | 3.0 | 474 | 0.7182 |
54
- | 1.0152 | 4.0 | 632 | 0.6720 |
55
- | 1.0152 | 5.0 | 790 | 0.6444 |
56
- | 1.0152 | 6.0 | 948 | 0.6201 |
57
- | 0.6533 | 7.0 | 1106 | 0.6068 |
58
- | 0.6533 | 8.0 | 1264 | 0.5954 |
59
- | 0.6533 | 9.0 | 1422 | 0.5895 |
60
- | 0.5543 | 10.0 | 1580 | 0.5840 |
61
- | 0.5543 | 11.0 | 1738 | 0.5777 |
62
- | 0.5543 | 12.0 | 1896 | 0.5731 |
63
- | 0.4994 | 13.0 | 2054 | 0.5735 |
64
- | 0.4994 | 14.0 | 2212 | 0.5735 |
65
- | 0.4994 | 15.0 | 2370 | 0.5736 |
66
 
67
 
68
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5850
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
  - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 64
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
+ - lr_scheduler_warmup_steps: 0.06
47
  - num_epochs: 15
48
  - mixed_precision_training: Native AMP
49
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 7.9411 | 1.0 | 158 | 0.8584 |
55
+ | 5.7966 | 2.0 | 316 | 0.6884 |
56
+ | 4.6457 | 3.0 | 474 | 0.6328 |
57
+ | 4.1820 | 4.0 | 632 | 0.6210 |
58
+ | 3.8281 | 5.0 | 790 | 0.5837 |
59
+ | 2.7451 | 6.0 | 948 | 0.5861 |
60
+ | 2.3142 | 7.0 | 1106 | 0.6141 |
61
+ | 1.8199 | 8.0 | 1264 | 0.6588 |
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:645290db7d016116934187972026d75c5ef943b759e91b7fa43686080492ec9e
3
  size 1911406472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e770e35697421f428ad1dcc95ba93ebc507612dc32af085f5f331a96720ea355
3
  size 1911406472