Training in progress, step 2500

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "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": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04189da0ade7534ebf00f974e3e36a27bf642d1fb796c954c290d85e293aead8
+oid sha256:38273929027c458def5b2cd0aa2e6d03b43df8c55df0df81cb50c449315ed4f1
 size 7087984

runs/Apr13_18-41-09_5a453ccd3267/events.out.tfevents.1713033677.5a453ccd3267.2298.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1b42c90898735d5961ad8ad25c40fc4ba606f940945fa4ee35d69557677352
-size 7782
+oid sha256:af93c37d5e210e64614346ca04874cfa6b409b629787457590cd0e0fa027ac6f
+size 8264

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c57aad0bc99a4ef6e927fe78d9566e5b7baf068bf746a9811ef2aa58cb9e4f
+oid sha256:8891a401e2b5a8defd1a4d66fe5189073b0869bc834715840eea44756b063b03
 size 5112