Training in progress, step 2500

adapter_config.json

@@ -10,18 +10,18 @@
   "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",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 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:d8ed11eb5b1827cd8a1d578d4ee50a73537a2c96f23d02a3a67a0f4c48e7c1a0
-size 894624
+oid sha256:b701015ede0583a7f7e9e33e9534e3f2c51dfb61f8fe2641912c2ad3ebf1e704
+size 1779432

runs/Apr13_18-17-46_5a453ccd3267/events.out.tfevents.1713032268.5a453ccd3267.2298.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011fc725a5240c3287a80ae0fbcf1087656c47486cfd71bbc4aa325d25bca7df
-size 7782
+oid sha256:178ed403da9950da89d3166938b0dfe88527b8494f9da7c42a35df6060dc64e8
+size 8264

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c644b433f0c0e785d3bc10f899fc0ad9f7057eaf6e9012c85373f7af903cd9
+oid sha256:d050b43edd7c50f88496e38be705946bbda3ce56e0b456627f1f16fed28b14f5
 size 5112