Training in progress, epoch 1

adapter_config.json

@@ -12,19 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "down_proj",
     "v_proj",
-    "q_proj"
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_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:c333f38c6b93518b1a685090f8c7e1e682bd2162a54f54e1ba8bfdbaffa1a511
-size 1858776
+oid sha256:f9a51739cc531fbcf1a6913e8e3a543b2c9205f3ac4352d96c25c1f6cab6b5e3
+size 39131224

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc38c1434562e9247268c03fa7c53ae1f3f4e00c44e028ae38391686d923fb7
+oid sha256:b1de24a4f658f25bc557b19c3cf10642709679c3667fb36499704e04b17000ae
 size 5304