Training in progress, epoch 0

adapter_config.json

@@ -9,19 +9,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "k_proj",
+    "q_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa9ed65767a1c5bf472fc551098fbf96f4669be162665287b2c1326e32b2cbd
-size 27297032
+oid sha256:ba5b7e430ec0f618c0b6d7ef26ac67df9bd8429b34cff28c3f7cb9e0aa8811a8
+size 109086416

runs/Feb29_17-39-22_azure-jap/events.out.tfevents.1709228363.azure-jap.98070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088939b74a25b72d40e528a0f4ece6025154265233d15b931b41926274c7e84e
+size 15204

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608bc2aeb704ee007228ce05771320912e465432790f2336f9c619c7b87612c6
+oid sha256:89da3dd596957004e5c2f903a7bb273c1c8af67b0b5e0238af698c27934b398b
 size 4859