Training in progress, step 100

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5b3243f9e80b3c9b64cc5c0b43a0786b4e715ca790b7a842ea30c1c22ee6d8
+oid sha256:e91ff697f1f59cb04d85105920d479a14db54708bacdc3132da05bec0c9dd0b0
 size 25272360

runs/May05_22-31-16_poseidon/events.out.tfevents.1714948312.poseidon.1517230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99d58ba74c6c4666ed1e450d4bc15c472eba63c071cfb19b000347d746c40f2
+size 9631

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b8cfbedba7789e90affee0e9476148210f11c52e5d1cde6e63bbbc715e1d0d
+oid sha256:e11f181e67e96fff8e17778aee9d6145e26ab1d7f389af5c1f2dabdb3dc0a25d
 size 5048