Model save

README.md

@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the wsc dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3459
-- Num Input Tokens Seen: 49376
+- Loss: 0.3492
+- Num Input Tokens Seen: 46944
 
 ## Model description
 
@@ -75,6 +75,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.17.1
 - Transformers 4.51.3
-- Pytorch 2.9.0+cu128
+- Pytorch 2.9.1+cu128
 - Datasets 4.0.0
 - Tokenizers 0.21.4