Training in progress, epoch 0

adapter_config.json

@@ -9,21 +9,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_head",
-    "q_proj",
+    "down_proj",
     "k_proj",
+    "up_proj",
+    "o_proj",
     "v_proj",
-    "o_proj"
+    "q_proj",
+    "lm_head",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a40a33b2095ef68951b2591bcd7d7d1c80fd43e9c59cc8e3f5e84d67fa70a5
-size 1635341408
+oid sha256:a82200c5c64bd499bdc7e66f4645de4f73578d32329a3a87eb26ad31f3b317ae
+size 605753040

runs/Jun26_16-44-10_admim-Precision-5820-Tower/events.out.tfevents.1719400457.admim-Precision-5820-Tower.591996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525655680d4b1e59910b4e0405834fcaef3075c31023ccd8d4769a7d5f50b26a
+size 4848

runs/Jun26_16-46-32_admim-Precision-5820-Tower/events.out.tfevents.1719400594.admim-Precision-5820-Tower.592841.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af20121f2decf4276fc816d6da87103da5008294de7377b70666692d345d74f
+size 7010

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f3227d29bd02491c47f380a124850e5555bcefa0b7801c15988a2586f529a7
+oid sha256:087fab87112a82b7316c6d8ba3249f41c747d4d68aae66ae5c2bc64af0ad79b1
 size 4792