Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -19,8 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "lm_head",
     "v_proj",
-    "q_proj"
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c191652737f406a8a471bd2258c04272b603ec77bd1ec1306145e7c45b76af3
-size 109069176
+oid sha256:9b923f7d5f59e9a76fa559d0524882b3d37361c8c69fb431480c86b17ccc7e12
+size 1204678496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8b295a048d13c5b6d5bc2393229c75f2c2b6238e75c21d743bed36200aeee5
+oid sha256:ab77fc0e9f0403350fb1d7952560231ba95e2f6110966483b495f868d10eb050
 size 4984