Training in progress, step 800

adapter_config.json

@@ -26,12 +26,12 @@
   "target_modules": [
     "o_proj",
     "up_proj",
-    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
     "lm_head",
     "down_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59d9cf6c84f574218b74947f827eb3528f214cc8316075b8bc288fc23b72aaa
+oid sha256:bfc171754052268c491a77528615b43bfe5afd7a6e22a53df3bdcd433ad85c66
 size 632223152

runs/Jul03_21-15-32_aice006/events.out.tfevents.1751557534.aice006

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5631fc73d5f47c4110a6d628bae15e8dd55a8e4bff8ec8a126cd49562f48b451
-size 67143
+oid sha256:e690968b7b1bdcd4eb05e4e54265de53b51574439f4457119325da14811eca2e
+size 128543

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3761bb5640c8839ba9a181666d5759c5fa28b79ba7df3ebb49411318407e15
+oid sha256:673c02420c5c0759bec9f011d6fc57276a4c66627feb50dbdea3c774377ad770
 size 6328