Training in progress, epoch 0

adapter_config.json

@@ -9,22 +9,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 2,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "up_proj",
-    "down_proj",
-    "gate_proj",
+    "k_proj",
     "o_proj",
     "q_proj",
+    "down_proj",
+    "gate_proj",
     "v_proj"
   ],
   "task_type": "SEQ_CLS",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4269d4ac3e94c52258d31cbdf6e2897a1e4fb807db452835d2d7b37917466be
-size 2946609584
+oid sha256:58e53a80ed29f16cdd3801d512a15e6c45b29af63a54c71b5f87bdfff6db9022
+size 283223752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b29f09d61fdf50ff19f4c24988a948069bd79e762a1cf68e2b2e09f3a63f67
+oid sha256:186d4a8d5e284e001aba263dbdd99b1efa3e780c9807dc7682d2a270d62a7dc3
 size 4728