Training in progress, epoch 2

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cab62878c942d6ff2a9ef848dd51d11d056ab4962a08b2cfdd0a6ed8e8241dc
-size 1090646616
+oid sha256:00a98af9483dd6d40eda48d4530f1e3df75158f691c129a633d655785cd905c0
+size 1132590104

runs/Apr06_11-21-37_90d0c6419ce2/events.out.tfevents.1712402501.90d0c6419ce2.789.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03230b78960a93475e24748423694d2b2523bb8455794d03554276bdcee971f
-size 5860
+oid sha256:a0d5b32c6ecb328826cca92d46b0761aa3c9ec0638d79170a78a30a9e91155f4
+size 6476

training_args.bin

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