Training in progress, epoch 1

adapter_config.json

@@ -13,18 +13,20 @@
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head"
+  ],
   "peft_type": "LORA",
   "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
+    "up_proj",
+    "q_proj",
     "down_proj",
     "gate_proj",
     "v_proj",
-    "up_proj",
-    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650086e1b083bf5a1342f1e7e22661afaf370eaa81c4f221d52ca829de3bd8a7
-size 1342239008
+oid sha256:6f7493a5ae6420ca73642d1ce4a49da2b50cce4281c2b3d257253eb40ecf1337
+size 1604645504

runs/Apr17_01-49-10_ubuntu2204/events.out.tfevents.1713332953.ubuntu2204.15251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7a9cf6b5dd21d3acdd79a1bf31c378327aca06ffb366a7d9c7f7aee0eaf876
+size 5091

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3253e9567d5fbcf40febe8cf0bed0a54647c6eb4fd522bb71663633062e751e
+oid sha256:8e945a2218d38e3be4cf8289c408a86eeb86063450ec94382df6b3deac010f95
 size 4728