End of training

README.md

@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8908
-- Bleu Global: 28.3278
-- Gen Len: 7.5328
+- Loss: 2.9171
+- Bleu Global: 28.0878
+- Gen Len: 7.4973
 
 ## Model description
 
@@ -35,13 +35,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-06
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -56,8 +56,10 @@ The following hyperparameters were used during training:
 | 0.0294        | 6.0   | 3804 | 28.9421     | 7.5008  | 2.7144          |
 | 0.0253        | 7.0   | 4438 | 28.5901     | 7.5542  | 2.8013          |
 | 0.0176        | 8.0   | 5072 | 28.4891     | 7.5348  | 2.8497          |
-| 0.0155        | 9.0   | 5706 | 2.8761      | 28.5233 | 7.5419          |
-| 0.014         | 10.0  | 6340 | 2.8908      | 28.3278 | 7.5328          |
+| 0.0155        | 9.0   | 5706 | 28.5233     | 7.5419  | 2.8761          |
+| 0.014         | 10.0  | 6340 | 28.3278     | 7.5328  | 2.8908          |
+| 0.0167        | 11.0  | 6974 | 2.8892      | 28.2921 | 7.502           |
+| 0.0161        | 12.0  | 7608 | 2.9171      | 28.0878 | 7.4973          |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805595e2ae66ce4a330e06ca28a98f13954e843f8f75eea408712203e3c24364
+oid sha256:73eda5ee9cf32ff01a29e8c1552a48af8854603707302725e40ddbf82d6070d5
 size 5905