RP-Dataset : 1.27 Epoch : Loss values 0.3x

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": ".\\BlackSheep",
+  "_name_or_path": ".\\KOOWEEYUS/BlackSheep-RP-12B",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 131072
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.44.0"
+  "transformers_version": "4.44.2"
 }

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362efb3ba4a759abeb7fd7a066b224ab5afe86358fd551a86b8961bd939e4482
+oid sha256:4d92cfdfdc02e0f0c6b87de7a282155e97677fbf89a8d9ce1ad78f37432c49f5
 size 4865522496

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194ee130b090116a1e17c5677c5747af7231fa61fa939a88b6fea262455a5444
+oid sha256:e3fe56dda5866015c50acd4b78cd9f5b746bf321866c7d32e364fffd4d558472
 size 4907529424

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0275596a3dd0e6567ef738b9d0d67ff7563ae0d10b735f272a6b3d651fa63111
+oid sha256:666048d4c95b649e1adc6482c1659821d44b586bb7a8306b968d1b4ed4d3ea76
 size 4907529456

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8c363a90c9dac56f2f29d66ac70effb50d52c6331acf4bcf56469fe8e039203
+oid sha256:6461b0ffc0031983bbb5f365293b94c0ff446ca3d7ca099f66839328e8d019a4
 size 4907529456

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28315decd44bcb531bdd72200e78851c583aebc6c53a0dc513f33aa995b382b
+oid sha256:387b824bcfc68f547ff4f9024d264e1867ac88ac2c6e6eafede084467a299b7d
 size 4907496272