English to arabic model trained using Quran-Classical-Arabic-English-Parallel-texts

README.md

@@ -6,22 +6,24 @@ tags:
 metrics:
 - bleu
 model-index:
-- name: working
+- name: en-ar-model
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/boghdady95/huggingface/runs/wq61zns9)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/boghdady95/huggingface/runs/wq61zns9)
-# working
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/boghdady95/huggingface/runs/i9kdffyd)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/boghdady95/huggingface/runs/i9kdffyd)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/boghdady95/huggingface/runs/i9kdffyd)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/boghdady95/huggingface/runs/i9kdffyd)
+# en-ar-model
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.1143
-- Bleu: 21.836
-- Gen Len: 67.4314
+- Loss: 0.1630
+- Bleu: 49.2887
+- Gen Len: 28.6434
 
 ## Model description
 
@@ -46,23 +48,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 312  | 0.1450          | 13.6092 | 66.5229 |
-| 0.1446        | 2.0   | 624  | 0.1337          | 15.8043 | 67.4747 |
-| 0.1446        | 3.0   | 936  | 0.1267          | 17.6106 | 67.2133 |
-| 0.1222        | 4.0   | 1248 | 0.1217          | 18.8785 | 67.4451 |
-| 0.1031        | 5.0   | 1560 | 0.1190          | 19.5595 | 67.1748 |
-| 0.1031        | 6.0   | 1872 | 0.1170          | 20.6884 | 67.7779 |
-| 0.0937        | 7.0   | 2184 | 0.1158          | 21.133  | 67.3496 |
-| 0.0937        | 8.0   | 2496 | 0.1148          | 21.4563 | 67.4739 |
-| 0.0859        | 9.0   | 2808 | 0.1144          | 21.8952 | 67.3031 |
-| 0.0814        | 10.0  | 3120 | 0.1143          | 21.836  | 67.4314 |
+| 0.1741        | 1.0   | 1250 | 0.1632          | 49.2836 | 28.626  |
+| 0.1551        | 2.0   | 2500 | 0.1630          | 49.3258 | 28.6074 |
+| 0.144         | 3.0   | 3750 | 0.1630          | 49.2887 | 28.6434 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3be33f1220564c548265394cc062a0115fcef7afc18e00aebfdc8d735eaf8e7
+oid sha256:4f12d391e5f431e1de396adbcc1c003d0de6eb99540fa33792c2c5857df4365c
 size 305452744

runs/Aug04_23-35-32_6a18a6ce128c/events.out.tfevents.1722814543.6a18a6ce128c.34.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e93d43d10b5ffce06e3a2b9d54ba9c103b27b5426f2ccf4bef249ad09f77f62
-size 7986
+oid sha256:d8bcae812ffbad39d5217eea183965489e7d984b0b9e8365aa2612729060d702
+size 8710