Training in progress, step 400

adapter_config.json

@@ -20,14 +20,18 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
     "k_proj",
-    "v_proj",
-    "o_proj"
+    "q_proj",
+    "lm_head",
+    "down_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:fabafb9a6c2613bfe257882b18a404808a41f9d979bbaa06345b7ac9dc53ffcd
-size 13648488
+oid sha256:fcd10f6ecd3d72c2abfbf45f641ebc8fbd870aa0c082d3ea8f3f2093d12c661e
+size 632223152

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5631fc73d5f47c4110a6d628bae15e8dd55a8e4bff8ec8a126cd49562f48b451
+size 67143

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad941b85e2737cc3a51a357bf9c2ba8e5bb80b6538f67dbc2dbf65b92ae394b7
+oid sha256:673c02420c5c0759bec9f011d6fc57276a4c66627feb50dbdea3c774377ad770
 size 6328