End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [zake7749/gemma-2-2b-it-chinese-kyara-dpo](https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7677
+- Loss: 3.0069
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -43,21 +43,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.4381        | 0.64  | 200  | 2.2165          |
-| 1.9414        | 1.28  | 400  | 2.3546          |
-| 1.5135        | 1.92  | 600  | 2.3314          |
-| 0.7845        | 2.56  | 800  | 2.8106          |
-| 0.5724        | 3.2   | 1000 | 3.4573          |
-| 0.2391        | 3.84  | 1200 | 3.4574          |
-| 0.1169        | 4.48  | 1400 | 3.7176          |
-| 0.0685        | 5.12  | 1600 | 3.7769          |
-| 0.0195        | 5.76  | 1800 | 3.7677          |
+| 2.3853        | 0.64  | 200  | 2.1371          |
+| 1.9709        | 1.28  | 400  | 2.1690          |
+| 1.6145        | 1.92  | 600  | 2.1344          |
+| 1.1069        | 2.56  | 800  | 2.4925          |
+| 0.849         | 3.2   | 1000 | 3.0008          |
+| 0.5224        | 3.84  | 1200 | 3.0069          |
 
 
 ### Framework versions