Model save

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0011
+- Loss: 0.0000
 
 ## Model description
 
@@ -45,13 +45,20 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.2
-- training_steps: 100
+- training_steps: 800
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0007        | 0.2222 | 100  | 0.0011          |
+| 0.0533        | 0.2222 | 100  | 0.0132          |
+| 0.0           | 0.4444 | 200  | 0.0000          |
+| 0.0           | 0.6667 | 300  | 0.0000          |
+| 0.0           | 0.8889 | 400  | 0.0000          |
+| 0.0           | 1.1111 | 500  | 0.0000          |
+| 0.0           | 1.3333 | 600  | 0.0000          |
+| 0.0           | 1.5556 | 700  | 0.0000          |
+| 0.0           | 1.7778 | 800  | 0.0000          |
 
 
 ### Framework versions