Training complete

README.md

@@ -4,6 +4,8 @@ base_model: Helsinki-NLP/opus-mt-en-jap
 tags:
 - translation
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: translate-en-ja
   results: []
@@ -16,13 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-jap](https://huggingface.co/Helsinki-NLP/opus-mt-en-jap) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 6.5227
-- eval_bleu: 0.0056
-- eval_runtime: 137.6772
-- eval_samples_per_second: 14.897
-- eval_steps_per_second: 0.24
-- epoch: 0.0408
-- step: 80
+- Loss: 3.6965
+- Bleu: 0.2251
 
 ## Model description
 
@@ -50,6 +47,10 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.41.2

runs/Jun20_07-17-05_d2c5626bf4c8/events.out.tfevents.1718870307.d2c5626bf4c8.24.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f684f15f1649e4f036a332a928dfad6c8e4839b9fd130c319896585bfb7b35
+size 407