oddadmix/masrawy-english-arabic-translator
Browse files
README.md
CHANGED
|
@@ -11,11 +11,11 @@ model-index:
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
#
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 2.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -40,33 +40,14 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
-
| Training Loss | Epoch | Step
|
| 49 |
-
|
| 50 |
-
|
|
| 51 |
-
| 2.6732 | 2.0 | 4792 | 2.5879 |
|
| 52 |
-
| 2.4873 | 3.0 | 7188 | 2.5003 |
|
| 53 |
-
| 2.2897 | 4.0 | 9584 | 2.4407 |
|
| 54 |
-
| 2.2402 | 5.0 | 11980 | 2.4038 |
|
| 55 |
-
| 2.1045 | 6.0 | 14376 | 2.3795 |
|
| 56 |
-
| 2.032 | 7.0 | 16772 | 2.3621 |
|
| 57 |
-
| 1.9792 | 8.0 | 19168 | 2.3410 |
|
| 58 |
-
| 1.9129 | 9.0 | 21564 | 2.3319 |
|
| 59 |
-
| 1.8975 | 10.0 | 23960 | 2.3192 |
|
| 60 |
-
| 1.8107 | 11.0 | 26356 | 2.3170 |
|
| 61 |
-
| 1.7901 | 12.0 | 28752 | 2.3128 |
|
| 62 |
-
| 1.7654 | 13.0 | 31148 | 2.3061 |
|
| 63 |
-
| 1.6899 | 14.0 | 33544 | 2.3042 |
|
| 64 |
-
| 1.6535 | 15.0 | 35940 | 2.3061 |
|
| 65 |
-
| 1.6733 | 16.0 | 38336 | 2.3027 |
|
| 66 |
-
| 1.6643 | 17.0 | 40732 | 2.3029 |
|
| 67 |
-
| 1.6471 | 18.0 | 43128 | 2.2996 |
|
| 68 |
-
| 1.6138 | 19.0 | 45524 | 2.3013 |
|
| 69 |
-
| 1.5878 | 20.0 | 47920 | 2.3011 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
|
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# masrawy-english-arabic-translator
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.9310
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 1
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 3.1506 | 1.0 | 2396 | 2.9310 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 305452744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1934c7ad8286128b729374e8ad273bb4e052e2090a8fd78df2ce7944c2ac5ea
|
| 3 |
size 305452744
|
runs/Nov21_04-32-01_ncgki16hjz/events.out.tfevents.1732163523.ncgki16hjz.3733.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ded7518d3ae7b3902741b33cf0f5b259431b773eb8395478b95d2a420da870b3
|
| 3 |
+
size 6425
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef6646a5e31f8ac2f8a2353eeac69fcafa1f56e70aff74172b394edc5b9dd418
|
| 3 |
size 4792
|