Training in progress, epoch 0

adapter_config.json

@@ -9,7 +9,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -17,17 +17,17 @@
     "lm_head"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "v_proj",
     "gate_proj",
+    "down_proj",
+    "q_proj",
     "k_proj",
+    "v_proj",
     "up_proj",
-    "q_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114df29e5ad31a61bd50b6989f12652b112289dc3e774f2b3629a303f1365d51
-size 1132590104
+oid sha256:0cab62878c942d6ff2a9ef848dd51d11d056ab4962a08b2cfdd0a6ed8e8241dc
+size 1090646616

runs/Apr06_11-32-59_95ba8f3e0cb8/events.out.tfevents.1712403182.95ba8f3e0cb8.419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821c13c43105405c21fc7a3980afb00d047842d83da1cc536a0e6a3ddc8ec7b9
+size 5244

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f48e910c5f01ebcecf5cec2f4731ab4fd94fa30ed0be2744dfe04b2f9c65e251
+oid sha256:db107a659e36681c588786c4c1f79eeff989b22f58b53f8873df602a1cf6b26c
 size 4728