Training in progress, step 2500

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_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:b701015ede0583a7f7e9e33e9534e3f2c51dfb61f8fe2641912c2ad3ebf1e704
+oid sha256:6dc624739c8dcffcf3dfcd2a382b79167a259cfe36fa041b1aaab66ac85fbb47
 size 1779432

runs/Apr13_18-18-51_27edc8b3c5f1/events.out.tfevents.1713032332.27edc8b3c5f1.273.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8959a13d9910d1e59c6cf0ea89da737cdd2a1413025bd34716f760c7f74a1f2
-size 7782
+oid sha256:f5a229178b6edb45a3208bdea4a0c4405343cec4d1cc77f59a2bf709efea3e49
+size 8264

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d050b43edd7c50f88496e38be705946bbda3ce56e0b456627f1f16fed28b14f5
+oid sha256:938d39ff700d0244770c7f67aec933c1856e8118c1b2a173ace2ca39804cf841
 size 5112