Training in progress, epoch 0

adapter_config.json

@@ -27,11 +27,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "v_proj",
-    "q_proj",
     "dense",
-    "o_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b21fdcdc9a65cf5f8d06ca171d6ec8e09e189ea26caf4edd762a75a3352e7f
+oid sha256:b27cb8a4a92ba14d321837469faebebb769adb447a1e27584cc76e9086329795
 size 2732672640

runs/Jun04_06-21-54_raycluster-training-coreweave-gpu-group-worker-88787/events.out.tfevents.1749018154.raycluster-training-coreweave-gpu-group-worker-88787

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f074c68d798757aa3eaabbef68107b317fbca1ee525735cd4c273cec855cae8b
+size 7028

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5541bcb592c19bf3a50648bfd7147f8e5f289ed96d239633694053ef71414502
-size 5816
+oid sha256:e7717fc4105221c10be7b9a08616747adabc4072c548785dd8f4dc567afb007f
+size 6225