Training in progress, step 200

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.3,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "dense_4h_to_h",
+    "query_key_value",
     "dense_h_to_4h",
-    "query_key_value"
+    "dense",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6122248efad15f08bb35ef89dbfb4db02d69860b1a9b820e62900a2fb0d6353
-size 1579384
+oid sha256:f816a8a531e54985983c04a38199b6bee45d3cf3617f018f55aa098c8f7dc1da
+size 399632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c25f947011cdcfeb2e2cd6b6797fb101f0c43353904140320fa5ceb0b490467
+oid sha256:f9577e2af7afb07c1d7a1aeeecfd7678c692b1dad8317f69302400bc7232785f
 size 6712