Training in progress, step 2500

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:b1a37bb4c088783a956e81866f7121a24877ca0fff624dd785183d962c12169d
+oid sha256:e7168b42dd52043bdaa155ab48af7780bb1b4d81207feef54e67032cf32472d0
 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 sha256:64f6f8d893b2098e62c5c2b7a7a26a59e3c3a71a8843c28442da6c3019e343e9
-size 157204
+oid sha256:e92a5cefd1b2793d44cb7c8c8a6ad28ea258f02e41a59de67de8c4b055dde204
+size 163544

training_args.bin

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