Training in progress, epoch 1

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5be520c1c19e55201b404a24747172aa211568df1468101f7420a5f27b72674
+oid sha256:920f90492b983056b7f47519a2ef1375608b021b87b6d8617ae85514d80d0278
 size 18893616

runs/Jul20_14-40-55_cmle-training-13669393038079472133/events.out.tfevents.1721486456.cmle-training-13669393038079472133

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a919bf8e67dbfc7eb66f97d81d052dfdc6c9f0a5b5a835c46b71ba6a8e95a739
+size 7783

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00ac591a99e9872ef76e8517d2c8b3021f58138bc213ca8c8e6d97752637b56
+oid sha256:97e742e0588f19998138fea0049b74f0fb38873746807daa6bbbd8d1580750b6
 size 4731