Training in progress, step 100

adapter_config.json

@@ -15,17 +15,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
-    "up_proj",
+    "k_proj",
+    "down_proj",
     "q_proj",
-    "gate_proj"
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df096199927ddbdde200b1c71b8c291651dc6e208429f57711ce6ceef6530b2
-size 100060536
+oid sha256:d3f3e71a4da3a39a6cf7fdcb8dd60e4b87c3164ba403028d7d427b1b50a08331
+size 200068904

runs/Apr11_22-49-38_deep-diver-main-rare-husky-1-0-0/events.out.tfevents.1712890281.deep-diver-main-rare-husky-1-0-0.520.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9533a1e5b09043cf2b202b59d59cf89a93c9b47849c11735a807e0c6b99d65d
+size 14482

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8bd01b1aed0eccc61952c0117f4b0f1694e5f940bfc0eefb917e5f0275884f2
+oid sha256:5e40efaf1ad8aaee40eb10508cecfe994c7d5d8ef3fa5ed3a0c0e553833fe313
 size 5112