Training in progress, step 1900

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "k_proj",
-    "up_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
+    "up_proj",
     "down_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1acd296c54230e9a9ad524623323df163ea8161b6aca990eb5c4cb9cc9f8772f
+oid sha256:54798f2a6282f0a65c44df86892cbd31aa136ff2a51ff333aac18e3fce19f662
 size 671150064

runs/May11_22-24-47_gpu4-119-5/events.out.tfevents.1715430380.gpu4-119-5.1225720.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a790a2f5ff9b9f2702ed1170c370cf7a15a126dce9a1a5a20c2df5b2d40d6282
-size 119164
+oid sha256:0da4eeb6ec55b42547770955c383b84ce0c71f34f7eccbdf32cbe56d515d6048
+size 125504

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475012aaba5e592a35fecc87b8cbd2410e93eed2254dffdcefde98525e0fbb07
+oid sha256:a05f96ec090263376cd228d635aca352f8b6b4cf2b5f952fe5cee47667e6313e
 size 5816