Model save

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5_1.5b_500k_16kcw_4ep
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on the anghabench dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0009
+- Loss: 0.0007
 
 ## Model description
 
@@ -56,9 +56,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step   | Validation Loss |
 |:-------------:|:------:|:------:|:---------------:|
 | 0.0014        | 0.9981 | 61000  | 0.0017          |
-| 0.0014        | 1.9962 | 122000 | 0.0010          |
-| 0.0017        | 2.9944 | 183000 | 0.0008          |
-| 0.0003        | 3.9925 | 244000 | 0.0009          |
+| 0.0015        | 1.9962 | 122000 | 0.0010          |
+| 0.0018        | 2.9944 | 183000 | 0.0006          |
+| 0.0003        | 3.9925 | 244000 | 0.0007          |
 
 
 ### Framework versions