Training in progress, epoch 2

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "gate_proj",
-    "down_proj",
+    "o_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
-    "v_proj"
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5697d67a065ae81855dc1ceae12cbc3c0d0f4422e70c24d01a13dec57181e626
+oid sha256:ce47c6be3bf4e289f7310f5525882d9f8350a402f1aeb7bdb4dbcfd0fc09e5c4
 size 1073864104

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c11a6ac886e89a098471690b6ced3af1fbd2cdfd12722f5d9b47d3d1327018d
-size 11422878
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3d1c9623a34b05e5276e76b44a731d67950fe9c67b5350a8e5d92641f17908
+oid sha256:66287c45113b67d50497fb3a1f0c125d4c6a0d8493a9d870ad867a59697997c2
 size 7288