Training in progress, step 200

adapter_config.json

@@ -34,12 +34,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "gate_proj",
     "down_proj",
     "q_proj",
+    "k_proj",
     "up_proj",
     "o_proj",
-    "k_proj"
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6ffbbc3ef1f6459a42262c20daa57644415f98821543c7715481de3e049f96
-size 71320216
+oid sha256:004a710a01739ae3c15a50d64e44652fec98d5ecb61417891e3231a60dc3e913
+size 69157536

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 199999,
+  "eos_token_id": [
+    200020
+  ],
+  "max_length": 131072,
+  "pad_token_id": 200029,
+  "transformers_version": "5.5.0"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcf8ec8306b4f270411b96a1434505a36b36c0a56d79284f15e47d93ed13462
+oid sha256:4aa2e3325989e8434fe3c0f7564866f88b52c2009f394bc964c603eedb7a1a38
 size 5649