Training in progress, epoch 1

adapter_config.json

@@ -9,18 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bd620c1e931f20050c5df785edaf1e9e39ffb13f90e64c1c61eb4823cf5b02
-size 18034152
+oid sha256:f203c1de07917558563e76d94d1198537fe37e59ae8f4dc502c2d39ef1193d45
+size 403743472

runs/Mar18_18-20-59_594498a00ca2/events.out.tfevents.1710786065.594498a00ca2.692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec907e4e965f735f7d1075522842e976a550d84c266592838316a9b52759d5a
+size 5824

runs/Mar18_18-23-41_594498a00ca2/events.out.tfevents.1710786229.594498a00ca2.692.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1793c335d89946109fa840b2ac8d4bffcc9061521487f82ec9c1aa271c4dad
+size 11724

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd78465fec827fdf3d4bc227ac4399fbb41cfacfa97bee663d7c4f37a60cab2f
+oid sha256:6772462cd9d56d4bb8c90908f90b31fe0c999d962951e75e9ede86f0ff05ccc4
 size 4920