Training in progress, step 2500

adapter_config.json

@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "down_proj",
+    "o_proj",
     "v_proj",
     "up_proj",
     "lm_head",
-    "o_proj",
-    "down_proj",
+    "k_proj",
+    "q_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbd1aca725b3183bf90c2ad81c47daf254a9e34660bde292a2321767f25b1b28
+oid sha256:4f4b6fd505248cee59153f464d4316e0c2fe0b7bdcee8ce5b0edde1ae082058b
 size 1444314856

runs/May15_18-07-38_65dce0afb0d7/events.out.tfevents.1715796494.65dce0afb0d7.270.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a346b2c093112dc273b0beeadaa459153a3afa6abf75fc3850e54ac1ed5b4ad6
+size 5915

tokenizer.json

@@ -499,6 +499,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3832bbe8f12dc8d106c5e91b2845a13a91138fdfa52ffea44408c8213dac86c4
-size 4984
+oid sha256:2bac58446bb3b22351af58ecf1b4b1bc7fd82b4dc87646e153ff65d629d199a6
+size 5112