Training in progress, epoch 1

adapter_config.json

@@ -9,10 +9,11 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 1024,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +21,13 @@
     "ln_f"
   ],
   "peft_type": "LORA",
-  "r": 512,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
     "k_proj",
-    "q_proj",
     "o_proj"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c78aa949438bb8c0980b3fc65948161c0201f70b095df439c8aae88b5ce33df
-size 1744865936
+oid sha256:b39a3ae13c445e49174db721ea509017ea053ff93f109ce2775e6bf141911f4c
+size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72b4966c1a054d2740acf0d62bbb169106a7d0c8de41c285f1ed3a37dc27bd9
-size 4920
+oid sha256:cc345772b28458d4d95975f32ce988df2baf3dfda666150e6ea093e6a45703e1
+size 4984