Training in progress, epoch 0

adapter_config.json

@@ -28,10 +28,10 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "dense",
-    "v_proj",
     "q_proj",
-    "o_proj"
+    "v_proj",
+    "o_proj",
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b24d8a978c000cda4c11ad81049c1d0e53a4e34b100e064bcae1ed3fb46b47d
+oid sha256:03b25f7fbe6470dc0fbb7b09ae3ccd818be3d3a74986e58c80583b5ebfd5e35c
 size 2732672640

runs/Jun02_20-12-39_job-name-e75bed-raycluster-7f5d7-wg-worker-p9z2k/events.out.tfevents.1748895175.job-name-e75bed-raycluster-7f5d7-wg-worker-p9z2k

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b4b98cad2b13cfaf7026872b7de0c5d1d70531d1930001d3418c7fd1cd2ec4
+size 7037

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00cf35f73fe53ccde37019e6f1ccddbf1a6cfa37990b18f8320d82aafa014849
+oid sha256:10e4482bb810d09ae7e94cc147b01b251650aef3787039659acd51325bf21514
 size 5816