End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8846
-- Bleu: 17.7229
-- Gen Len: 32.719
+- Loss: 2.0112
+- Bleu: 14.7086
+- Gen Len: 31.718
 
 ## Model description
 
@@ -44,15 +44,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 2.1397        | 1.0   | 625  | 1.9092          | 17.03   | 33.143  |
-| 1.956         | 2.0   | 1250 | 1.8846          | 17.7229 | 32.719  |
+| 2.1899        | 1.0   | 625  | 2.0112          | 14.7086 | 31.718  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d324140ec51dfb9cb8896decd64b7378e6ab0cfb3f41f5f31dbd8ce6859a241
+oid sha256:c9f219efc2cf9bd45a1e0f3b9dc096aa57b49de799f5c542a86c70e707c0ebf4
 size 2460354912

runs/Apr23_06-42-47_8907be7fe176/events.out.tfevents.1713854569.8907be7fe176.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1046a36af2869c3f50acb848f7fc6ba2e4634df09f6af9b09f76f7d424b3eb
+size 5919

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdb8b3ede5a746a5a96d7f393811cf8c04d3012c8abb9aebf3fec681c2f6d1d
+oid sha256:db86ac10f315ec15aaae1ec889572866f6a13f6e6049d2d9c4b1c7541636bd27
 size 5048