oddadmix/masrawy-english-arabic-translator-opus-big-v2.8-only-claude-eval-as-test

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2840
+- Loss: 1.2957
 
 ## Model description
 
@@ -40,7 +40,7 @@ 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: 6
+- num_epochs: 8
 
 ### Training results
 
@@ -60,6 +60,11 @@ The following hyperparameters were used during training:
 | 2.0185        | 4.98  | 12000 | 1.2850          |
 | 1.9523        | 5.4   | 13000 | 1.2834          |
 | 1.9215        | 5.81  | 14000 | 1.2840          |
+| 1.9375        | 6.23  | 15000 | 1.2893          |
+| 1.9386        | 6.64  | 16000 | 1.2846          |
+| 1.9254        | 7.06  | 17000 | 1.2953          |
+| 1.9059        | 7.48  | 18000 | 1.2982          |
+| 1.873         | 7.89  | 19000 | 1.2957          |
 
 
 ### Framework versions

runs/Jan03_16-24-38_n1zykf2whs/events.out.tfevents.1735921495.n1zykf2whs.160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126d3881086a65177cb100df81fcf810a653935789113577cc41c6a5e332dde8
+size 8352

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc8cae6af7ea74b64ab3f9013750faa5f46f7653b8879282a6074b418202d71
+oid sha256:4f6d26a029bb56923b700b1c0002a2c631b3c7bc3136112313315e4d96fec452
 size 4856