Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
     "down_proj",
-    "q_proj",
-    "gate_proj",
-    "k_proj",
-    "v_proj"
+    "gate_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:b3859e88c47aeace90549c2d6b1f1e921c268be5553fe921d19768d21e1c97af
+oid sha256:d6b61b571d67828427b2d92a8f0b857069181047d97b0c9286a168c2b784cdd4
 size 2332095256

runs/Apr02_07-12-39_1f3fbe1ee1c0/events.out.tfevents.1712041966.1f3fbe1ee1c0.32401.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28bcc9c2d888f08d7b8fc2e3b341bf7a912e166686b6c707570d4948dff2d40f
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c93f4241534784d984a7e3b976dec8e33542a9bd517c3b2795bd4e33062913
+oid sha256:114b4cb8725f1816f2141e390e912ce51e3d5062aad6e9e02174514a5a238740
 size 4984