Instructions to use AMAJEED2003/en-ur-mt-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AMAJEED2003/en-ur-mt-mini with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("AMAJEED2003/en-ur-mt-mini") model = AutoModelForSeq2SeqLM.from_pretrained("AMAJEED2003/en-ur-mt-mini", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files- README.md +7 -9
- generation_config.json +0 -1
- 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 [Helsinki-NLP/opus-mt-en-ur](https://huggingface.co/Helsinki-NLP/opus-mt-en-ur) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Bleu:
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -44,19 +44,17 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
-
- num_epochs:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.1447 | 4.0 | 1000 | 0.9039 | 21.3957 |
|
| 59 |
-
| 0.1478 | 4.8 | 1200 | 0.9057 | 21.6706 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ur](https://huggingface.co/Helsinki-NLP/opus-mt-en-ur) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8459
|
| 21 |
+
- Bleu: 22.8909
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
+
- num_epochs: 2
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 54 |
+
| 0.2081 | 0.32 | 200 | 0.8459 | 23.1875 |
|
| 55 |
+
| 0.2441 | 0.64 | 400 | 0.8479 | 22.8478 |
|
| 56 |
+
| 0.177 | 0.96 | 600 | 0.8455 | 22.3542 |
|
| 57 |
+
| 0.1771 | 1.28 | 800 | 0.8459 | 22.8909 |
|
|
|
|
|
|
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
generation_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"decoder_start_token_id": 62024,
|
| 5 |
"eos_token_id": 0,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token_id": 0,
|
| 3 |
"decoder_start_token_id": 62024,
|
| 4 |
"eos_token_id": 0,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 303858340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f002839e50b1705c96a561c0d2f4e82da508053a8c7b3721ae10442a3202719
|
| 3 |
size 303858340
|