Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "gate_proj",
+    "k_proj",
     "down_proj",
     "q_proj",
     "o_proj",
-    "k_proj"
+    "v_proj",
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c2b237a9d6e4f42820f11fb6a46e7fa64092ce0eaf8bfe6216180cfe7ee76f
-size 19644912
+oid sha256:944cf343c86cbebbc88bbc9eec916c38b59ee756e5ca3f40b329793e70672265
+size 39256960

runs/Jun10_02-23-10_48ddfe8e991f/events.out.tfevents.1717986227.48ddfe8e991f.24991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d861e8fdcb8ab33521f816094d557f098434e51bf075a9be09c921c2eabd5e
+size 10218

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6164f388be3134a1410d2df7cb67c45da1f045de939f2b7ed85aac05e799d67
-size 5176
+oid sha256:d1ffb27f0fd6a7143dd5c1775871c7ef4697a68201a714b4e32514ace64902a5
+size 5304