tjasad/translation_slo_eng_opus-mt-sla-en_lora

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Helsinki-NLP/opus-mt-sla-en
+metrics:
+- bleu
+model-index:
+- name: translation_slo_eng_opus-mt-sla-en_lora
+  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. -->
+
+# translation_slo_eng_opus-mt-sla-en_lora
+
+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: 1.6979
+- Bleu: 35.6045
+- Gen Len: 12.8817
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- 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
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 1.8938        | 1.0   | 2500 | 1.6979          | 35.6045 | 12.8817 |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

runs/May21_17-00-30_770b8cbb3c1c/events.out.tfevents.1716310830.770b8cbb3c1c.4323.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9add0d567a0592339f1f72343217990c4fcc73008b2f97eebcddce448bf233
-size 6687
+oid sha256:19a18333f75f764bfb357f0a46c120ec762729a8df24ee2d382e1cc678ac3090
+size 7411