Training in progress, step 500

adapter_config.json

@@ -10,8 +10,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.1,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,8 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a404df577dede634ea736604a622e6ec0d1d79721b8d9bba2046a0eb6cf48b7
-size 2369344
+oid sha256:bccd8efc267c34f895593b57d6d6f092428c744c154b32ad072aafcd2075c658
+size 3554032

runs/May24_04-46-36_1caf850506a5/events.out.tfevents.1716525996.1caf850506a5.1083.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2b437c87a0b104c11babc321cb3686724fd430b12931f71021d76945d9f792
+size 5843

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:558b81e643642554350f209ef08a652de29ac3d69f294a891c8a38c1e2e87600
+oid sha256:0c434b1efa0e7e0f6445bd6a42604717af567402a7028faa5313efaf940b8aea
 size 5176