Training in progress, epoch 1

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9e5e79028211a978f71fe49088a3e24255ab9799078f1d3e8ec4cf7c616e8c
+oid sha256:b1d9d9de67962fc352d2c8d415c437721a7b0679a49c931bdadf8a0d6b925757
 size 671150064

runs/Apr08_04-42-31_allennlp-cirrascale-68.reviz.ai2.in/events.out.tfevents.1712576745.allennlp-cirrascale-68.reviz.ai2.in.115384.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822ae927c2096e3f942236803c8a50c61af35eaeaca87d6c84ca0ee18e0fa0c1
+size 103955

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0b2f97f60873a850e81ee9df4527cca1aa5a13b4975d9f906de4db1726f077
-size 5112
+oid sha256:9304f74d27f82b5a3074ddff9ca7df542535152f54c988d11f5d22ece2f414e1
+size 5176