Training in progress, step 50

adapter_config.json

@@ -20,12 +20,20 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc2",
-    "q_proj",
-    "(proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)",
     "v_proj",
+    "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)",
     "fc1",
-    "qkv"
+    "(proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)",
+    "k_proj",
+    "lm_head",
+    "qkv",
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:747e8d2f58da64cce06b2242456c7cfef6fce3dbf6b8413324907b6132b26eb9
-size 28481560
+oid sha256:0080c0f8b30d62a747646740f969c0c51f91815a0852773620d79e548ee27bdb
+size 2284139392

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12a4a0f72c994d82f5acbe01d47016da84d1ba58b0985461f389e6bcbb1c9fb
+size 6464

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5847b55f6a78d10ea7b51923898af8045ff2d53d1a22d4bf1c551ea01d55abe7
+oid sha256:1a8454129b802355cdd303a732094048a6a05139e0a10ebda31dc940d3a4a9ea
 size 5496