Training in progress epoch 3

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.0009
-- Validation Loss: 4.4255
-- Train Bleu: 0.0568
-- Train Gen Len: 34.5116
-- Epoch: 2
+- Train Loss: 3.8234
+- Validation Loss: 4.4239
+- Train Bleu: 0.0641
+- Train Gen Len: 33.3488
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 4.4659     | 4.4875          | 0.0102     | 99.2093       | 0     |
 | 4.2023     | 4.4382          | 0.0588     | 34.8372       | 1     |
 | 4.0009     | 4.4255          | 0.0568     | 34.5116       | 2     |
+| 3.8234     | 4.4239          | 0.0641     | 33.3488       | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1717064477.fe870d1f5381.172.6.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb3adbddfe9493688807739f8b02053260cef80c108f190ea1e8acddcc88407c
-size 4102091
+oid sha256:7e8558810db487a3113f45b99b6b9fd4b1bdc3e5a1ae5f6690c32c1dcf609218
+size 4102298

logs/validation/events.out.tfevents.1717064481.fe870d1f5381.172.7.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47153270fc61e73b8b85d0c9e73b3b5a1f9d3630419e42259fde89cd247e834a
-size 541
+oid sha256:46ae98b80b722fb7bad67b575a97b60228e6214ce8ac74a2725b063252e14f51
+size 696

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4d591163ed0c0c358891a84b529c1298aba3c4c0ea6140c41eed6318a0fe9b
+oid sha256:55360b80fb0157991b328f7d562311268f2f3f28dc1bf395a2ef89a683a842c7
 size 312320596