End of training

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/gemma-2-9b-it-bnb-4bit](https://huggingface.co/unsloth/gemma-2-9b-it-bnb-4bit) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7063
-- Acc: 0.45
-- Log Loss: 2.7062
+- Loss: 1.3774
+- Acc: 0.35
+- Log Loss: 1.3774
 
 ## Model description
 
@@ -46,14 +46,18 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 20
-- num_epochs: 1
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Acc  | Log Loss |
 |:-------------:|:-----:|:----:|:---------------:|:----:|:--------:|
-| 3.5673        | 1.0   | 10   | 2.7063          | 0.45 | 2.7062   |
+| 3.0058        | 1.0   | 10   | 1.8528          | 0.4  | 1.8527   |
+| 2.9092        | 2.0   | 20   | 1.7207          | 0.45 | 1.7206   |
+| 2.6161        | 3.0   | 30   | 1.5368          | 0.4  | 1.5367   |
+| 2.3656        | 4.0   | 40   | 1.4192          | 0.35 | 1.4191   |
+| 2.1831        | 5.0   | 50   | 1.3774          | 0.35 | 1.3774   |
 
 
 ### Framework versions