Training in progress, step 200

adapter_config.json

@@ -10,17 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value"
+    "query_key_value",
+    "dense_4h_to_h",
+    "dense_h_to_4h",
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86b6ad3ea44f94f57c888c35dd39d6be9acf8746b1ee81a891f280d1314a6ac
-size 1183112
+oid sha256:9cfbf85a88bd132dbca599b2801ab4e81ee9c388aa3c028c3b7815f2765f6a87
+size 4731832

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3723e0d4a88248bbec20abffa6f8cb683c5a4be32d58d3d573094a8e77b0f61d
+oid sha256:8807c1d78d4dc6797f28372f858f1bc8000fbf68ee4085845fa850083e832b42
 size 6072