Training in progress, step 100

adapter_config.json

@@ -24,10 +24,8 @@
     "q_proj",
     "gate_proj",
     "down_proj",
-    "k_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
+  "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6846e05d229019632070879e028e2fd8c467895c522afc40ed7bf8cf9e99cf8e
+oid sha256:cf38e7df3e0d06f0ff725d26355c1c1b43b826180a2b1db31be390c14a21a673
 size 671150064

runs/Apr05_19-37-28_allennlp-cirrascale-50.reviz.ai2.in/events.out.tfevents.1712371480.allennlp-cirrascale-50.reviz.ai2.in.48043.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9057ca52b5042c74af3b4ad90ede982957dff2e85358bb962dfdb633e701e42
+size 13382

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d888e8e973b2c3d22f2404c1e9ed7a4c45b883ef323d3488caaf3c18e4d220ad
-size 5112
+oid sha256:6aed5e0579321afe046a90c0cc3a32c7d4cff2e81f00dc7223fdf2c95545813e
+size 5048