Training in progress, epoch 2

adapter_config.json

@@ -10,23 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "q_proj",
-    "o_proj",
-    "up_proj",
     "v_proj",
-    "k_proj"
+    "q_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:db9190cdfc8df7fd645d8dd0bfd8702d052caae1e2c3216943c35227f30ad881
-size 236063560
+oid sha256:69d8e46d815eb7cdbbddfc26029803bce391234f4e325dc323fcfede5c20c6e7
+size 23641256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889b2160592deeaa54fc416447dce84ba88884fd0a7255d72c7f0cc8b89c6de2
+oid sha256:8e03afd26b548836b213df2e2397fa92b30de1cf4d10c9d60ccbb2cd5cf85c3b
 size 5560