Training in progress, step 400

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "up_proj",
-    "gate_proj",
     "down_proj",
     "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe0a2351f0f22a1ac4584ac734f8bc00d6afff09e3df614070f6ac3a2402f35
+oid sha256:bdad58eccfdceb30752f806b2ff357a91edbeafd504f061fbbda26a09756b502
 size 2684416208

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

runs/Apr21_16-58-14_e02/events.out.tfevents.1713733110.e02

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb959d75b80e5e104b85ea7985ad59027d05d0a3d275c101f26013cb47460486
+size 13407

tokenizer.json

@@ -152,6 +152,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f4ff7fb8b6e4de2b051c8c4ec9a4d200edc390be50360d35e1b68111694f89
-size 4984
+oid sha256:c28af4fdc9821354834943949d9628c727ac75ba4675b5e0069c5787a1b52677
+size 5048