oddadmix/bi-msa-egyptian-translator-masrawy
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 1.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
|
|
| 41 |
- total_train_batch_size: 64
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
@@ -86,6 +86,29 @@ The following hyperparameters were used during training:
|
|
| 86 |
| 1.9764 | 4.72 | 18500 | 1.5331 |
|
| 87 |
| 1.9808 | 4.85 | 19000 | 1.5334 |
|
| 88 |
| 1.9739 | 4.98 | 19500 | 1.5331 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
|
| 90 |
|
| 91 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.4636
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 41 |
- total_train_batch_size: 64
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 8
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
| 86 |
| 1.9764 | 4.72 | 18500 | 1.5331 |
|
| 87 |
| 1.9808 | 4.85 | 19000 | 1.5334 |
|
| 88 |
| 1.9739 | 4.98 | 19500 | 1.5331 |
|
| 89 |
+
| 1.9662 | 5.1 | 20000 | 1.5374 |
|
| 90 |
+
| 1.9696 | 5.23 | 20500 | 1.5322 |
|
| 91 |
+
| 1.9535 | 5.36 | 21000 | 1.5301 |
|
| 92 |
+
| 1.9555 | 5.49 | 21500 | 1.5271 |
|
| 93 |
+
| 1.9459 | 5.61 | 22000 | 1.5255 |
|
| 94 |
+
| 1.9548 | 5.74 | 22500 | 1.5205 |
|
| 95 |
+
| 1.9538 | 5.87 | 23000 | 1.5171 |
|
| 96 |
+
| 1.9409 | 6.0 | 23500 | 1.5158 |
|
| 97 |
+
| 1.918 | 6.12 | 24000 | 1.5129 |
|
| 98 |
+
| 1.9415 | 6.25 | 24500 | 1.5102 |
|
| 99 |
+
| 1.9168 | 6.38 | 25000 | 1.5097 |
|
| 100 |
+
| 1.9131 | 6.51 | 25500 | 1.5093 |
|
| 101 |
+
| 1.9205 | 6.63 | 26000 | 1.5068 |
|
| 102 |
+
| 1.913 | 6.76 | 26500 | 1.5058 |
|
| 103 |
+
| 1.9098 | 6.89 | 27000 | 1.4675 |
|
| 104 |
+
| 1.9093 | 7.02 | 27500 | 1.4663 |
|
| 105 |
+
| 1.9044 | 7.14 | 28000 | 1.4656 |
|
| 106 |
+
| 1.9047 | 7.27 | 28500 | 1.4650 |
|
| 107 |
+
| 1.9103 | 7.4 | 29000 | 1.4641 |
|
| 108 |
+
| 1.9002 | 7.53 | 29500 | 1.4637 |
|
| 109 |
+
| 1.8961 | 7.66 | 30000 | 1.4641 |
|
| 110 |
+
| 1.895 | 7.78 | 30500 | 1.4638 |
|
| 111 |
+
| 1.9073 | 7.91 | 31000 | 1.4636 |
|
| 112 |
|
| 113 |
|
| 114 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470068592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c155144d1301dc565cecfdee1c1022016370cbfa321f4c211a11f2a781b1ee38
|
| 3 |
size 1470068592
|
runs/Aug12_15-06-07_nap6s17oyh/events.out.tfevents.1755011188.nap6s17oyh.81.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8124b5b279843ca4a6c33305c7820d534c106cf688b8cde6d72e1601a5abd29e
|
| 3 |
+
size 8848
|