Training in progress, step 4000

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:c6f7b5f10aa27e60f26aefd502521b1a30475bd20f88682745ce7cc4c22ba8de
+oid sha256:7ca38834728c77a11e13525ea1f0ee97c0935b9c1c7df42175061edbf9b20a7c
 size 9457520

runs/Sep05_14-16-25_9a76d9e283dc/events.out.tfevents.1725545787.9a76d9e283dc.372160.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6059ffd033d4e8d60d84415f97876a1d975830f771fe954341e43f6ae73b60fd
-size 5519
+oid sha256:e81aa3567555c1cc75b7f7bd54c55622c8d934ad1a671f45e767f5ef3eceb8ed
+size 5730

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99215d4e6048352aca78987d05844c5348a848bc4c537b015670cba027258f82
+oid sha256:5b25f2878401c234c9383813c9a0aae1f4b93a35eb3da32b2a9bdf17fb62b895
 size 5304