Training in progress, step 2500

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "value",
-    "query"
+    "query",
+    "value"
   ],
   "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 sha256:834e4672eb867f9a19b1df7af4c6343424821cb6c92336d871afb6d3403f9f86
-size 1790664
+oid sha256:721dcffc4f51041c4198a6e36ac4e13b0e8f76eee734a2d3bcbf79b892fc477b
+size 3560232

runs/Apr13_17-04-33_ef033c8b66bb/events.out.tfevents.1713027875.ef033c8b66bb.375.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bcc0897fd80b9abd2d2b654c539caab77d54d536a930b4e28b983222dcafba
-size 10957
+oid sha256:0e44e1fa2dd121808898268e4c1c6d080a37ce411adef4800748d5acdd46b0ca
+size 11439

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b065f422fdea6bdc2c70844fee113f18418cd093bbc94434e8bba4ff85f61b
+oid sha256:af55b1aeec5ed6308bd309963296c8152b5222112da0f30ebbf39b9047fb198f
 size 5112