Training in progress, epoch 1

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1d9d9de67962fc352d2c8d415c437721a7b0679a49c931bdadf8a0d6b925757
+oid sha256:18b5c90c26956b3a1ca61dd4821676997f191e4b601d6ce87f5b96db85006cbb
 size 671150064

runs/Apr08_05-45-54_allennlp-cirrascale-68.reviz.ai2.in/events.out.tfevents.1712580439.allennlp-cirrascale-68.reviz.ai2.in.118396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e973087aed9896970ff1656f856b706ca9b7528448ed75f91dbe98b9d75bd59
+size 66794

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9304f74d27f82b5a3074ddff9ca7df542535152f54c988d11f5d22ece2f414e1
+oid sha256:9d9cd0868ed2e5cbd16cf1d37714af36365460aa0c5cfcc847d69c45f46d52f8
 size 5176