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 sha256:01020c68189dc4df31cc8ab06c6cba737341861fdb37c77eac8db305b65cb4eb
-size 1744865936
+oid sha256:18c1691c8b8cc8b59213f5348c4f38cc140aa38b71c83e3e13016432447026a4
+size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7c93ac31847190cf16267efb879d435df667269e1649fcba6c3516e3dfea4f
-size 4920
+oid sha256:43411814fd2055a976b329880ad0608c7b9331ec7f884dbe9e0842e948b16710
+size 4984