Training in progress, step 1400

adapter_config.json

@@ -20,20 +20,20 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "o_proj",
+    "lm_head",
+    "(proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)",
     "gate_proj",
-    "(2): Linear8bitLt(in_features=5120, out_features=3584, bias=True)",
-    "down_proj",
     "fc2",
-    "up_proj",
-    "(0): Linear8bitLt(in_features=5120, out_features=5120, bias=True)",
+    "(2): Linear8bitLt(in_features=5120, out_features=3584, bias=True)",
+    "q_proj",
+    "v_proj",
+    "qkv",
     "fc1",
-    "(proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)",
     "k_proj",
-    "lm_head",
-    "qkv",
-    "o_proj",
-    "q_proj"
+    "(0): Linear8bitLt(in_features=5120, out_features=5120, bias=True)",
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa57bbefadb87bdd4a5bc796854f8df579bf38bee305c47f46c479578b1231fc
+oid sha256:4cde9403622748aff9e0a13d8d3113892b2235f2ab9fc21ddccb6e8fe3b8cf0f
 size 2284139392

runs/Nov12_20-56-02_a100-largegpu/events.out.tfevents.1731445126.a100-largegpu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31de3ad88d077edb419f53156f955e6f642872cf2712ec0f22150ae03f6b4bb3
-size 25470
+oid sha256:4c5d19e03e47265fdfb68d4e5e1149df3a5ee56fdf0647561e02444377d7bb3e
+size 25681

runs/Nov13_01-53-53_a100-largegpu/events.out.tfevents.1731462835.a100-largegpu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26cc5960b08d0fe2ea7e742fb4ae30d4ed0ba181477ddac59bf877003214cd18
+size 6468

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8454129b802355cdd303a732094048a6a05139e0a10ebda31dc940d3a4a9ea
+oid sha256:d3c8c3483e8381c83c4346fc02f9293b7bbdb0a029c9e471ddec3de2754d6b78
 size 5496