Training in progress, step 7750

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b6a1f4466bb6d8ca332d55275b5149442d5639837cbcb94da51633613a20ed
+oid sha256:fc0dbc386afc2466937437ddd89fca5bed2e2bdd8615c8547c9d4e5d3bc8e410
 size 2284139392

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3dd51e84fff5161e1bc0b77a39f8d5a0cab341112a738a43cbec084015b3b4
-size 67682
+oid sha256:1fb75728ed4403a8bb2d04456475864b132f2e67c4377d6a79a7cb0e74e3f318
+size 74170

runs/Nov14_00-28-34_a100-largegpu/events.out.tfevents.1731544126.a100-largegpu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987103120071b755791eb409a5c660d1d56fd2c1bef340d39d7ecb62a7301853
+size 6468

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c8c3483e8381c83c4346fc02f9293b7bbdb0a029c9e471ddec3de2754d6b78
+oid sha256:d272cf3cd6731b566de4f99491506324f032c4b4ff3326738e1700fef30c5103
 size 5496