Training complete

README.md

@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # m2m100_418M-en-hi
 
-This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
+This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6697
+- Loss: 0.9498
 
 ## Model description
 
@@ -49,14 +49,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9838        | 1.0   | 726  | 0.7157          |
-| 0.6961        | 2.0   | 1452 | 0.6745          |
-| 0.4105        | 3.0   | 2178 | 0.6697          |
+| 1.194         | 1.0   | 2263 | 1.0601          |
+| 0.8533        | 2.0   | 4526 | 0.9742          |
+| 0.6973        | 3.0   | 6789 | 0.9498          |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
-- Datasets 3.0.1
 - Tokenizers 0.19.1

runs/Oct22_09-46-17_7fc69030cd7f/events.out.tfevents.1729590381.7fc69030cd7f.6165.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5386ebd325dfd9db796cba0ef336a8455be0307665f252cdd28cec116a0ba3
-size 8613
+oid sha256:95461b401fdaef66fe8b01b888d5e15d354385c8f140a707f4ba61878e270750
+size 9238