Training in progress, epoch 1

adapter_config.json

@@ -13,22 +13,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
     "v_proj",
     "o_proj",
-    "down_proj",
-    "q_proj",
-    "up_proj"
+    "q_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:b3bc4f659a53f9f2b0eca9a162f07fbddae492a17820ca707fc2663833e8ff96
-size 45827920
+oid sha256:7f376b77cc6391bba68b51217cba064cab13f82ee75855596ea8ba543d3b8f22
+size 131251312