Training in progress, step 40

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded62283a71473a7a81066397e380ec9ce8ada4ba92e92dd6ad263082c291478
+oid sha256:fee0e5bbb239fc131f2b244c4dc8a7993f9946297255ecf0a1516eaa5059bc78
 size 31516744

runs/May14_18-09-56_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715710276.ip-172-31-69-60.ec2.internal.45873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01852e96143fe979567f52964c5258671d978737b7886857d9d672bfbcabc885
+size 6544

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a925774678852e0977560a67fd69a20001a407d91d0a08c8f775a475480c8b8
+oid sha256:947c23c145ef88048fe49ff21d6ec590423a9e9f85d9638ff29e711dd850176c
 size 6072