End of training

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.3879
+- Loss: 10.3856
 
 ## Model description
 

config.json

@@ -21,10 +21,10 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "thresholds": [
-    0.05315947160124779,
-    0.05315947160124779,
-    0.051153454929590225,
-    0.051153454929590225
+    0.0,
+    0.0,
+    0.0,
+    0.0
   ],
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790d51207554bce4f8afe0da3e768786814a4b0c3e6866058d31ff5771c936f7
+oid sha256:48c3f070255e4cd1990f87f887b31a1d643029725b341c2e621791a92d007473
 size 16750904