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",
@@ -20,14 +21,14 @@
     "ln_f"
   ],
   "peft_type": "LORA",
-  "r": 512,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
+    "v_proj",
     "k_proj",
-    "v_proj"
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122d052d7e15bee7c523091b95cfef4fc8282530a787fd5a4650bd4dc3d49bfd
-size 1744865936
+oid sha256:4318fb20a7998858b0f2396a8b282ca7a137f76669f16f30b52d72048347f168
+size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f67bf8baf64170a278918e0f142b307855494e5bc5143e84401cea48cbd8046
-size 4920
+oid sha256:1b9be52890a2cf01a4e4dbf8245b1dc0bf4bf52e3c6f4cbb1bdeb780e2d0204a
+size 4984