Training in progress, step 500

adapter_config.json

@@ -15,7 +15,7 @@
   "loftq_config": {},
   "lora_alpha": 256,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -25,13 +25,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "v_proj",
+    "down_proj",
     "q_proj",
+    "v_proj",
+    "up_proj",
     "k_proj",
-    "down_proj",
-    "o_proj",
-    "lm_head",
-    "up_proj"
+    "o_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 sha256:7fd9e253d6af3c5a009745c0a49331286413ce0f4f5dfcfcdacd303a86bd6b04
-size 238444008
+oid sha256:1abcf2252eb9af09d1d9cf5c7fee4b6de741348766e7d2529a83071e45b40e61
+size 156359640

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f846d36aae485459ed98faa0c0b1bdadf6bf66458553293b2754e96264b2078
+oid sha256:1293106fd389cd3ae65ccba0029bd0b842061e9a7ed1547d51f9cd3cadbe3a4c
 size 5752