Training in progress, step 100

adapter_config.json

@@ -20,11 +20,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "q_proj",
+    "down_proj",
     "up_proj",
     "k_proj",
+    "q_proj",
     "v_proj",
-    "down_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce03c51a64336d81ee92573277b153429a0c239dab8d5725e8ea214ad3159933
+oid sha256:e0c1d4f10632569318442534137b92aab1a229b5be31cd914a1d77f8f841a2de
 size 671150064

runs/Apr07_22-32-43_allennlp-cirrascale-68.reviz.ai2.in/events.out.tfevents.1712554686.allennlp-cirrascale-68.reviz.ai2.in.112442.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9850450f48cd16e9366069cbb9ce553e53824e8ddf624ece8b3162b55b0398b
+size 13463

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de29390fc5fa33a771ef9a696f8acb0d5bd2f530aa80c700260791ca6c209a94
+oid sha256:f6018217de31cac95bf99d6e7f09a1a51bb474ec4c53da48882fbbe67c13f810
 size 5112