ParitKansal commited on
Commit
311306e
·
verified ·
1 Parent(s): 84621f2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -28
README.md CHANGED
@@ -30,46 +30,94 @@ model-index:
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
- # marian-finetuned-kde4-en-to-fr
34
 
35
- This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
36
- It achieves the following results on the evaluation set:
37
- - Loss: 0.9620
38
- - Bleu: 50.5445
39
 
40
- ## Model description
 
 
41
 
42
- More information needed
43
 
44
- ## Intended uses & limitations
45
 
46
- More information needed
47
 
48
- ## Training and evaluation data
 
 
49
 
50
- More information needed
 
 
51
 
52
- ## Training procedure
53
 
54
- ### Training hyperparameters
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
- The following hyperparameters were used during training:
57
- - learning_rate: 2e-05
58
- - train_batch_size: 32
59
- - eval_batch_size: 64
60
- - seed: 42
61
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
- - lr_scheduler_type: linear
63
- - num_epochs: 1
64
- - mixed_precision_training: Native AMP
65
 
66
- ### Training results
 
67
 
 
 
 
68
 
 
 
 
 
69
 
70
- ### Framework versions
71
 
72
- - Transformers 4.47.1
73
- - Pytorch 2.5.1+cu121
74
- - Datasets 3.2.0
75
- - Tokenizers 0.21.0
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
+ # Marian Fine-Tuned KDE4 (English-to-French)
34
 
35
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) using the KDE4 dataset. It achieves the following results on the evaluation set:
36
+ - **Loss**: 0.9620
37
+ - **BLEU**: 50.5445
 
38
 
39
+ ---
40
+
41
+ ## Model Description
42
 
43
+ This English-to-French translation model has been fine-tuned specifically on the KDE4 dataset. The base model, Helsinki-NLP/opus-mt-en-fr, is part of the MarianMT family, renowned for its efficiency and high-quality neural machine translation capabilities.
44
 
45
+ ---
46
 
47
+ ## Intended Uses & Limitations
48
 
49
+ ### Intended Uses
50
+ - Translating English text into French.
51
+ - High-quality translations in the context of software localization, especially related to KDE4.
52
 
53
+ ### Limitations
54
+ - Performance may decline on texts outside the KDE4 domain.
55
+ - Struggles with idiomatic expressions, specialized technical jargon, or ambiguous content.
56
 
57
+ ---
58
 
59
+ ## Training & Evaluation Data
60
+
61
+ The model was fine-tuned on the KDE4 dataset, a specialized resource for machine translation in software localization. The evaluation metrics reflect the model's performance on this domain-specific data.
62
+
63
+ ---
64
+
65
+ ## Training Procedure
66
+
67
+ ### Hyperparameters
68
+ - **Learning Rate**: 2e-05
69
+ - **Train Batch Size**: 32
70
+ - **Eval Batch Size**: 64
71
+ - **Seed**: 42
72
+ - **Optimizer**: AdamW with `betas=(0.9, 0.999)`, `epsilon=1e-08`
73
+ - **LR Scheduler**: Linear
74
+ - **Epochs**: 1
75
+ - **Mixed Precision Training**: Native AMP
76
+
77
+ ### Results
78
+ - **Loss**: 0.9620
79
+ - **BLEU**: 50.5445
80
+
81
+ ### Training Loss Progression
82
+
83
+ | Step | Training Loss |
84
+ |-------|---------------|
85
+ | 500 | 1.2253 |
86
+ | 1000 | 1.2165 |
87
+ | 1500 | 1.1913 |
88
+ | 2000 | 1.1404 |
89
+ | 2500 | 1.1178 |
90
+ | 3000 | 1.0900 |
91
+ | 3500 | 1.0594 |
92
+ | 4000 | 1.0512 |
93
+ | 4500 | 1.0633 |
94
+ | 5000 | 1.0405 |
95
+ | 5500 | 1.0316 |
96
+
97
+ ---
98
+
99
+ ## Framework Versions
100
+ - **Transformers**: 4.47.1
101
+ - **PyTorch**: 2.5.1+cu121
102
+ - **Datasets**: 3.2.0
103
+ - **Tokenizers**: 0.21.0
104
+
105
+ ---
106
 
107
+ ## Example Usage
 
 
 
 
 
 
 
 
108
 
109
+ ```python
110
+ from transformers import pipeline
111
 
112
+ # Load the model
113
+ model_checkpoint = "ParitKansal/marian-finetuned-kde4-en-to-fr"
114
+ translator = pipeline("translation", model=model_checkpoint)
115
 
116
+ # Translate text
117
+ translation = translator("Default to expanded threads")
118
+ print(translation)
119
+ ```
120
 
121
+ This script demonstrates how to use the model for English-to-French translation tasks.
122
 
123
+ ---