Training in progress, step 2500

adapter_config.json

@@ -10,18 +10,18 @@
   "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": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8297a68fbafabfb33d432d9397a36e52fbd225edcbb4c1a232a61d0cbdf8b0cb
-size 7087984
+oid sha256:a8645d19db6845bb4564afd52a91514d8fc7f308ed7c413db1becb216835572c
+size 3549016

runs/Apr13_18-38-57_89a7766e7bdb/events.out.tfevents.1713033545.89a7766e7bdb.1873.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826d5a620da5a695376af410bc30ec85277bddee217fddc6f8de79c91cc3c5c3
-size 7782
+oid sha256:9ba91f32225e2730b6565e59a2207c719e008bac480a8dc77c6fe7384b44a9e6
+size 8264

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8891a401e2b5a8defd1a4d66fe5189073b0869bc834715840eea44756b063b03
+oid sha256:4f79fc44425c23e7c777e4d4c7c2a54250569b8587a209922ae3d63a708f7c3c
 size 5112