End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5957
+- Loss: 2.4040
 
 ## Model description
 

config.json

@@ -23,38 +23,38 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "thresholds": [
-    0.017051145434379578,
     0.023069201037287712,
-    0.049147434532642365,
-    0.051153454929590225,
-    0.05917752534151077,
-    0.06920761615037918,
-    0.0732196494936943,
-    0.07923770695924759,
-    0.08324974030256271,
-    0.07923770695924759,
-    0.089267797768116,
-    0.089267797768116,
-    0.0992978885769844,
-    0.0992978885769844,
+    0.03309928998351097,
+    0.04312938079237938,
+    0.05516548827290535,
+    0.07522567361593246,
+    0.09327983111143112,
     0.10531593859195709,
-    0.12136408686637878,
+    0.11935807019472122,
+    0.12738214433193207,
+    0.12738214433193207,
+    0.1313941776752472,
+    0.13340020179748535,
+    0.13941824436187744,
     0.1414242684841156,
-    0.15947842597961426,
-    0.1775325983762741,
+    0.15546639263629913,
+    0.1675025075674057,
+    0.18555666506290436,
     0.19157472252845764,
-    0.19759276509284973,
-    0.21765294671058655,
-    0.21765294671058655,
-    0.23169508576393127,
+    0.20762285590171814,
+    0.2196589708328247,
+    0.22768303751945496,
+    0.23771312832832336,
     0.2357071191072464,
-    0.23169508576393127,
-    0.225677028298378,
-    0.22968906164169312,
-    0.225677028298378,
-    0.225677028298378,
-    0.2457372099161148,
-    0.26980942487716675
+    0.23771312832832336,
+    0.24172517657279968,
+    0.24172517657279968,
+    0.24172517657279968,
+    0.24172517657279968,
+    0.24172517657279968,
+    0.23971915245056152,
+    0.2357071191072464,
+    0.225677028298378
   ],
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e178646fb43467fe1ac68c767dc53a190c62e7ab176499a24203913360d32b3
+oid sha256:0614f728766b92b1615c8d517b5974b34637fa328cbb4245781b4045b106c037
 size 4943163992

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c608913252c5ec911a52cc6a18aaad7787986220ee14dadd515f0a130e5be7d6
+oid sha256:3d4e08eef455b0c321fc81384f5b714615d206f3ed750833bd478342f7420cc5
 size 4999821144

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0199cb7cf5b42356ce1fa59a4fc571fcf15222f723459f2db7b81ef18a47d5d9
+oid sha256:d7af3748ac11c9732fca3ad1c359e63953a668eae233501094c8c6744b0f2ca5
 size 4540517840