Training in progress, step 150

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 512,
+  "lora_alpha": 1024,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 512,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
     "gate_proj",
-    "q_proj",
-    "o_proj",
     "up_proj",
-    "down_proj"
+    "v_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 sha256:1d72d153cd8e2fe89c33a87b3b0313b090c3f31cdeb7d95100a2b233836dfddd
-size 2684416208
+oid sha256:5f56db798d3ba06cd55ba1c72df9f01b66c623a9b5c024f78f0cedb2f2f0b794
+size 5368770952

runs/Sep19_09-43-38_3c2f58389953/events.out.tfevents.1726739023.3c2f58389953.3782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77de59d1c1b9f5063f05725affae9969d9c52f85346a62877907bacce855a4b2
+size 11459

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816bbcf2b1844a16fb3cb77a96cdabf72daf51a707885c0ab7f58feaafc31b45
+oid sha256:62a748e07b95603db1bde9c75216b67c03cc43db53e39bcaea28058b60fa5b2a
 size 5432