Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
+    "down_proj",
     "up_proj",
-    "k_proj",
-    "down_proj"
+    "gate_proj",
+    "q_proj",
+    "o_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:a88543787221afe021dffbaede5a56d77855d8c746aad4dcf50ef0c334a64f5d
+oid sha256:02d16376aae454e6928aee5f2230b660b97a945cc78a13e6819425c7d9f523d1
 size 2332095256

runs/Apr03_09-01-05_7e7dbb80658f/events.out.tfevents.1712134871.7e7dbb80658f.130441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25eeaba3877244591ac0846e6ece0c4f2cf500ad57ba244785ddecabf80f0dea
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6b7728ebd5084cc3d8f3eba3f5c02a8b62ec3cb6aa6428dde2a2a245350d95
+oid sha256:b77f2ec9f610235f340d725f469163605db795121bdc046515491f4dc8dac2d5
 size 4984