Training complete: English to Wolaytta translation model
Browse files- README.md +84 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Helsinki-NLP/opus-mt-en-mul
|
| 5 |
+
tags:
|
| 6 |
+
- translation
|
| 7 |
+
- en-wal
|
| 8 |
+
- wolaytta
|
| 9 |
+
- marian
|
| 10 |
+
- opus-mt
|
| 11 |
+
- generated_from_trainer
|
| 12 |
+
model-index:
|
| 13 |
+
- name: opus-mt-en-wal
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# opus-mt-en-wal
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-mul](https://huggingface.co/Helsinki-NLP/opus-mt-en-mul) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.3485
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 2e-05
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
+
- eval_batch_size: 16
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 3
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 56 |
+
| 0.6944 | 0.1396 | 1000 | 0.6297 |
|
| 57 |
+
| 0.5968 | 0.2793 | 2000 | 0.5214 |
|
| 58 |
+
| 0.5329 | 0.4189 | 3000 | 0.4742 |
|
| 59 |
+
| 0.5116 | 0.5585 | 4000 | 0.4459 |
|
| 60 |
+
| 0.4747 | 0.6981 | 5000 | 0.4255 |
|
| 61 |
+
| 0.4483 | 0.8378 | 6000 | 0.4120 |
|
| 62 |
+
| 0.4501 | 0.9774 | 7000 | 0.4021 |
|
| 63 |
+
| 0.4275 | 1.1170 | 8000 | 0.3899 |
|
| 64 |
+
| 0.4174 | 1.2566 | 9000 | 0.3833 |
|
| 65 |
+
| 0.406 | 1.3963 | 10000 | 0.3768 |
|
| 66 |
+
| 0.4145 | 1.5359 | 11000 | 0.3727 |
|
| 67 |
+
| 0.3968 | 1.6755 | 12000 | 0.3675 |
|
| 68 |
+
| 0.393 | 1.8151 | 13000 | 0.3635 |
|
| 69 |
+
| 0.4027 | 1.9548 | 14000 | 0.3595 |
|
| 70 |
+
| 0.3778 | 2.0944 | 15000 | 0.3573 |
|
| 71 |
+
| 0.3732 | 2.2340 | 16000 | 0.3556 |
|
| 72 |
+
| 0.3695 | 2.3736 | 17000 | 0.3535 |
|
| 73 |
+
| 0.3611 | 2.5133 | 18000 | 0.3518 |
|
| 74 |
+
| 0.3605 | 2.6529 | 19000 | 0.3504 |
|
| 75 |
+
| 0.3639 | 2.7925 | 20000 | 0.3491 |
|
| 76 |
+
| 0.368 | 2.9321 | 21000 | 0.3485 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.57.3
|
| 82 |
+
- Pytorch 2.9.0+cu126
|
| 83 |
+
- Datasets 4.0.0
|
| 84 |
+
- Tokenizers 0.22.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 308136760
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2135ef466dfb3e2d5d3572e292dd4324ec591f57d775172ef8b6840f75dda4e8
|
| 3 |
size 308136760
|