Training in progress, step 500

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd21bce58cd6f1b67a46c5ba4b28deb9dab27e678803f0cd87d59f12ae39d542
-size 27280152
+oid sha256:da0266b2d829ae02c56e186cd54539d8ca0b43464b683a51d1c85423ba4cb5d1
+size 4230006368

tokenizer.json

@@ -2338,85 +2338,69 @@
     ]
   },
   "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "<|begin_of_text|>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|eot_id|>",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "<|begin_of_text|>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|eot_id|>",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|begin_of_text|>",
-          "type_id": 1
-        }
-      },
+    "type": "Sequence",
+    "processors": [
       {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
+        "type": "ByteLevel",
+        "add_prefix_space": true,
+        "trim_offsets": false,
+        "use_regex": true
       },
       {
-        "SpecialToken": {
-          "id": "<|eot_id|>",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {
-      "<|begin_of_text|>": {
-        "id": "<|begin_of_text|>",
-        "ids": [
-          128000
+        "type": "TemplateProcessing",
+        "single": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          }
         ],
-        "tokens": [
-          "<|begin_of_text|>"
-        ]
-      },
-      "<|eot_id|>": {
-        "id": "<|eot_id|>",
-        "ids": [
-          128009
+        "pair": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          },
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 1
+            }
+          },
+          {
+            "Sequence": {
+              "id": "B",
+              "type_id": 1
+            }
+          }
         ],
-        "tokens": [
-          "<|eot_id|>"
-        ]
+        "special_tokens": {
+          "<|begin_of_text|>": {
+            "id": "<|begin_of_text|>",
+            "ids": [
+              128000
+            ],
+            "tokens": [
+              "<|begin_of_text|>"
+            ]
+          }
+        }
       }
-    }
+    ]
   },
   "decoder": {
     "type": "ByteLevel",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de903dff6a4584879db6512a2b3cd907b4d6a195d14e6c049cc8a18e0c6a0fa3
+oid sha256:4b14d20c6c5e870f0b338575500fa87c2941961ec67d884d28da36335032f79f
 size 5432