Training in progress, epoch 1

adapter_config.json

@@ -13,21 +13,19 @@
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "lm_head"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
     "o_proj",
     "up_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj",
-    "v_proj",
-    "k_proj"
+    "down_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:bcfde312f99adf0e68f08d150a9d2464cb54cf8d4685eac79df7785e4b0ea9e1
-size 1604645504
+oid sha256:8a97882c39114bed9dd3a1d0d421d1dcbc1c1a4ec961d367ac012581aa02a780
+size 1342239008

runs/Apr17_02-09-19_ubuntu2204/events.out.tfevents.1713334202.ubuntu2204.15826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd680529010dae663ae48b7c70dab496d5fdf7c0f65a7eb7ebaa26d38bdd633
+size 5091

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e945a2218d38e3be4cf8289c408a86eeb86063450ec94382df6b3deac010f95
+oid sha256:94cce6a5d87985b28f76df2a1e7f32e3b35cfc27842fa588def73204d1491948
 size 4728