Training in progress, epoch 0

adapter_config.json

@@ -13,21 +13,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 22,
+  "lora_alpha": 280,
   "lora_bias": false,
-  "lora_dropout": 0.03646305544053519,
+  "lora_dropout": 0.049207764529642734,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 56,
+  "r": 175,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "q_proj",
     "k_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78973e73b59d82d3c0f9c1c7e93bf3a7308922a036fa53ac860d2fe4b72881e7
-size 63684296
+oid sha256:f584325f0a9a1ddb8a1fbd9fe89139f37d0db253f4ff10b50957a9256a662d96
+size 198944992

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458f1affc5223205b1c70da9680fd973f05af853c52f2ca2f4d2b5a9731e29ec
+oid sha256:30fef994cbbbc9d16a7ee59897b473e8143042599513c53bdc815761349bb628
 size 7057