Training in progress, epoch 1

adapter_config.json

@@ -19,12 +19,12 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
   "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:ef39efd3ae20fc07dfb2567ae2d610c7c98726de6d3d9ef14d4eee1f3c170d68
-size 1025799272
+oid sha256:9eada2e509d7e18f688cfa702f0a6d6696af026980df2ab7ed5997a60d7f3301
+size 1027175696

special_tokens_map.json

@@ -6,7 +6,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e1cce57dcae8affff986cd131fcf02d234e8a97de506f3c648acd61ea818da
+oid sha256:94ccbfd39a9442ee2f2abd331d737eabb244286542b9c29a1489b6fb2ff3d9c6
 size 5560