Training in progress, step 15

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
     "up_proj",
+    "gate_proj",
+    "down_proj",
     "v_proj",
     "o_proj",
-    "down_proj",
-    "gate_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 sha256:016e62df04ec65529a38dd588f716fdaecf1b7d063f449f84b3291580dff92f2
+oid sha256:ecff1d71776426f7277227c80b2620c6cc122f1f38cd7fef2e8fbe1944c8dc22
 size 828527688

config.json

@@ -37,7 +37,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "vocab_size": 128256
 }

runs/Apr25_04-30-32_training-01/events.out.tfevents.1714019438.training-01.52176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75069b385b5d3f6326a490eb622f67fe68ce02fe72b207d58c8e1ba47c588fdb
+size 10012

tokenizer.json

@@ -2329,10 +2329,69 @@
     ]
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": true,
-    "trim_offsets": false,
-    "use_regex": true
+    "type": "Sequence",
+    "processors": [
+      {
+        "type": "ByteLevel",
+        "add_prefix_space": true,
+        "trim_offsets": false,
+        "use_regex": true
+      },
+      {
+        "type": "TemplateProcessing",
+        "single": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          }
+        ],
+        "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
+            }
+          }
+        ],
+        "special_tokens": {
+          "<|begin_of_text|>": {
+            "id": "<|begin_of_text|>",
+            "ids": [
+              128000
+            ],
+            "tokens": [
+              "<|begin_of_text|>"
+            ]
+          }
+        }
+      }
+    ]
   },
   "decoder": {
     "type": "ByteLevel",
@@ -2348,6 +2407,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": true,
     "vocab": {
       "!": 0,
       "\"": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b5f3a9294b75563476b806eee347de0294a1f6b9784bc9e9cf15233efba500
+oid sha256:33c270181dae82aff969aff9c90f69d7dc1388ef1fffb395c4a9a45efca78d06
 size 6328