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: 10.3529
-- Bleu: 0.0007
-- Gen Len: 175.3212
+- Loss: 5.1830
+- Bleu: 0.3807
+- Gen Len: 13.9075
 
 ## Model description
 
@@ -39,7 +39,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.003
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -50,15 +50,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len  |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
-| 10.4335       | 1.0   | 2500 | 10.3529         | 0.0007 | 175.3212 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| 5.4024        | 1.0   | 2500 | 5.1830          | 0.3807 | 13.9075 |
 
 
 ### Framework versions
 
 - PEFT 0.11.1
 - Transformers 4.40.2
-- Pytorch 2.2.1+cu121
+- Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

runs/May23_04-47-20_7e339963f90a/events.out.tfevents.1716439647.7e339963f90a.875.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ddbb99d5365777569f2f3307db1fc5795c8a5f6db767a26d735e76160dbbe1
-size 6714
+oid sha256:730c3e22b8cfbc65a2f50a30a5f3130a1d1e7c02672ba8400a31c64409936866
+size 7438