tjasad/translation_slo_eng_opus-mt-sla-en_prompt_tuning

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-sla-en](https://huggingface.co/Helsinki-NLP/opus-mt-sla-en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.1408
-- Bleu: 0.0005
-- Gen Len: 391.1274
+- Loss: 10.3529
+- Bleu: 0.0007
+- Gen Len: 175.3212
 
 ## Model description
 
@@ -40,8 +40,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len  |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
-| 10.5426       | 1.0   | 5000 | 10.1408         | 0.0005 | 391.1274 |
+| 10.4335       | 1.0   | 2500 | 10.3529         | 0.0007 | 175.3212 |
 
 
 ### Framework versions

runs/May21_14-46-06_8a1e3e8b9ecd/events.out.tfevents.1716302771.8a1e3e8b9ecd.433.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0004fee9d0e1783571293708c3e1eeddb4883413ee79ee919e53d6f4e7aa2a
-size 6714
+oid sha256:d443967cb416c56921e8a441fc24f2c77c3d339cd124f566dc2d26465e284637
+size 7438