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": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj",
-    "q_proj",
     "o_proj",
-    "v_proj",
     "gate_proj",
+    "k_proj",
     "down_proj",
-    "k_proj"
+    "v_proj",
+    "q_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:e024dd42370745139d905182e9d9e06c7c9db5e0335dea5b6af4f1da1146f93f
-size 19644912
+oid sha256:29263f010b73467d781a988233529cc0ea06e873173213a1833c46686d867d90
+size 78480320

runs/Jun10_09-38-09_48ddfe8e991f/events.out.tfevents.1718012562.48ddfe8e991f.334310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e131578fc61853c70dac7b9f7870e1129b70ac070922745fff04c24c89b409c9
+size 9955

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d004ae1f4948418450ba9b3eda16429c9b9279e9f9ee5b0508ea2c5a0d3e0fdb
-size 5176
+oid sha256:3d0e8578086c62d31c0054e61eeb3aad589514780d2ee582bbd68270ce238f7b
+size 5304